Projects
DeCipher

Cancer is a significant cause of morbidity and mortality worldwide. In Norway alone, there are more than 33,000 new cancer patients each year, and 11,000 cancer-associated deaths in 2017. A large proportion of these incidents are preventable. For example, a mass-screening program against cervical cancer established in the Nordic countries has demonstrated a reduction in morbidity and mortality almost by 80 %. Despite this success, it remains a significant challenge to improve the screening program, such as minimize over screening and undertreatment and hence reduce expenditure in a broad public health perspective.
Current knowledge about the disease, together with a wealth of available data and modern technologies, can offer far better-personalized prevention, by deriving an individual-based time till the next screening. Existing automatic decision support systems for cervical cancer prevention are, however, extremely conservative as they are mostly limited to identifying patients who are overdue for their next routine screening, without providing any personalized recommendations for follow-ups.
By intelligent use of existing registries and health data, DeCipher aims to develop a data-driven framework to provide a personalized time-varying risk assessment for cancer initiation and identify subgroups of individuals and factors leading to similar disease progression. By unveiling structure hidden in the data, we will develop novel theoretically grounded machine learning methods for the analysis of large-scale registry and health data.
DeCipher consists of an excellent multidisciplinary research team from diverse fields such as machine learning, data mining, screening programs, and epidemiology. Available to screening programs, clinicians, and individuals in the population, the DeCipher results will allow for an improvement of an individual’s preventive cancer healthcare while reducing the cost of screening programs.
SimulaMet’s Role
SimulaMet will play a central role in the development of machine learning algorithms for longitudinal screening data analysis. Moreover, as the coordinator, SimulaMet is responsible for overall project management and dissemination activities.
Funding source
Research Council of Norway, IKTPLUSS
All partners
Cancer Registry Norway
Karolinska University Hospital, Sweden
Lawrence Livermore National Lab, USA
Coordinator
SimulaMet
TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion

Data mining holds the promise to improve our understanding of dynamics of complex systems such as the human brain and human metabolome (i.e., the complete set of small biochemical compounds in the human body) by discovering the underlying patterns, i.e., subsystems, in data collected from these systems. However, discovering those patterns and understanding their evolution in time is a challenging task. The complexity of the systems requires collection of both time-evolving and static data from multiple sources using different technologies recording the behavior of the system from complementary viewpoints, and there is a lack of data mining methods that can find the hidden patterns in such complex data.
The goal of this multidisciplinary project is to develop novel data mining techniques to jointly analyze static and dynamic data sets to discover underlying patterns, understand temporal dynamics of those patterns, and capture early signs of future outcomes. We will introduce a scalable and constrained data fusion framework that can jointly factorize heterogeneous data in the form of matrices and multi-way arrays, by incorporating temporal as well as domain-specific constraints.
These methods will be motivated by a real, challenging system: the human metabolome, and used to jointly analyze static genetic information and longitudinal metabolomics data to discover interpretable patterns, i.e., subsystems corresponding to metabolic networks (networks of metabolites acting together), with the ultimate goal of understanding their role in the transition from healthy to diseased states. The project will play a significant role in terms of developing the data mining tools needed to extract meaningful information from the surge of data, referred to as "personal data clouds" being collected in predictive medicine studies, where participants give blood samples regularly to track their health status and will be alerted of early signs of diseases.
Funding Source
Research Council of Norway, IKTPLUSS (2020-2023)
Novo Nordisk Foundation, Exploratory Interdisciplinary Synergy Grant (2020-2022)
Partners
COPSAC (Danish Pediatric Asthma Center)
University of Copenhagen
University of Amsterdam
Publications for TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion
Talks, invited
Constrained Multi-Modal Data Mining Using Coupled Matrix and Tensor Factorizations
In SIAM Conference on Mathematics of Data Science, 2022.Status: Published
Constrained Multi-Modal Data Mining Using Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2022 |
Location of Talk | SIAM Conference on Mathematics of Data Science |
Type of Talk | Minisymposium talk |
URL | https://meetings.siam.org/sess/dsp_programsess.cfm?SESSIONCODE=74454 |
Journal Article
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
IEEE Journal of Selected Topics in Signal Processing 15, no. 3 (2021): 506-521.Status: Published
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2021 |
Journal | IEEE Journal of Selected Topics in Signal Processing |
Volume | 15 |
Issue | 3 |
Pagination | 506 - 521 |
Publisher | IEEE |
DOI | 10.1109/JSTSP.2020.3045848 |
Proceedings, refereed
PARAFAC2 AO-ADMM: Constraints in all modes
In 2021 29th European Signal Processing Conference (EUSIPCO). IEEE, 2021.Status: Published
PARAFAC2 AO-ADMM: Constraints in all modes
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2021 |
Conference Name | 2021 29th European Signal Processing Conference (EUSIPCO) |
Pagination | 1040-1044 |
Publisher | IEEE |
Talks, contributed
Exploring dynamic metabolomics data with multiway data analysis: A simulation study
In Virtual conference. SIAM Conference on Applications of Dynamical Systems, 2021.Status: Published
Exploring dynamic metabolomics data with multiway data analysis: A simulation study
Analysis of dynamic metabolomics data sets holds the promise to improve our understanding of the underlying mechanisms in human metabolism. That is crucial to detect the changes in the metabolism that can potentially lead to diseases. Dynamic metabolomics data has more than two axes of variation, i.e., samples, metabolites and time. While such time-evolving multi-way data sets are collected more and more in recent years, revealing the underlying mechanisms and their dynamics from such data remains challenging.
This talk will focus on a systematic study demonstrating the advantages and limitations of multi-way data analysis (also known as tensor factorizations) in terms of analyzing dynamic metabolomics data. We study different dynamic models of increasing complexity, i.e., a simple linear system, a yeast glycolysis model, a human cholesterol model, and generate data with different types of variation. Our numerical experiments demonstrate that despite the increasing complexity of the studied models, tensor factorization methods CANDECOMP/PARAFAC(CP) and PARAllel Profiles with LINear Dependences (PARALIND) can reveal the underlying mechanisms and their dynamics.
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | Virtual conference |
Publisher | SIAM Conference on Applications of Dynamical Systems |
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
In Asilomar Conference on Signals, Systems, and Computers, 2021.Status: Published
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
An effective way of jointly analyzing data from multiple sources is through coupled matrix and tensor factorizations (CMTF). Different characteristics of datasets from multiple sources require to employ various regularizations, constraints, loss functions and different types of coupling structures between datasets. While existing algorithmic approaches for CMTF can incorporate constraints, linear couplings and different loss functions, none of them has been shown to achieve the flexibility to incorporate all. We propose a flexible algorithmic framework for coupled matrix and tensor factorizations, which utilizes Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM). The framework facilitates the use of a variety of constraints, loss functions and couplings with linear transformations. Numerical experiments on simulated datasets and real data from chemometrics and hyperspectral super-resolution demonstrate that the proposed approach is accurate, flexible and computationally efficient with comparable or better performance than available CMTF algorithms.
While we focus on CANDECOMP/PARAFAC (CP) –based CMTF models, we will also briefly discuss the use of an AO-ADMM based algorithmic approach for fitting a PARAFAC2 model. We demonstrate that the proposed algorithmic approach enables imposing constraints in all modes, which has been a challenge using the traditional alternating least squares-based algorithm used for PARAFAC2.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | Asilomar Conference on Signals, Systems, and Computers |
Type of Talk | Invited Session Talk |
Tracing Dynamic Networks through Constrained Parafac2 Decomposition
In SIAM Conference on Applied Linear Algebra (LA21), Virtual Conference. SIAM, 2021.Status: Published
Tracing Dynamic Networks through Constrained Parafac2 Decomposition
Time-evolving data analysis is crucial for understanding complex systems such as the brain. Methods that assume static networks have successfully recovered spatial networks of connectivity from neuroimaging data. Still, discovering both underlying networks and their evolution is a challenging task.
To capture temporal evolution of connectivity networks, we arrange dynamic data as a tensor and use a tensor factorization method called PARAFAC2. PARAFAC2 deciphers the hidden structure of dynamic networks and yields unique and interpretable components. Preliminary results using PARAFAC2 in neuroimaging data analysis are promising. However, the constant cross-product constraint on the time-evolving mode hinders the use of additional constraints or regularization (e.g. spatial smoothness) on this mode. Currently, the only way to regularize the time-evolving mode of a PARAFAC2 model is with a flexible coupling approach, which finds the solution through regularized least-squares subproblems. Instead, we use an alternating direction method of multipliers (ADMM) based approach to widen the possible regularization penalties to any proximable function.
Our numerical experiments demonstrate that the proposed ADMM-based algorithmic approach for PARAFAC2 can accurately recover the underlying evolving components, is flexible in terms of imposing constraints and also computationally efficient.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | SIAM Conference on Applied Linear Algebra (LA21), Virtual Conference |
Publisher | SIAM |
Talks, invited
A Flexible Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorizations based on the Alternating Direction Method of Multipliers
In Europt21, 18th Workshop on Advances in Continuous Optimization, 2021.Status: Published
A Flexible Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorizations based on the Alternating Direction Method of Multipliers
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | Europt21, 18th Workshop on Advances in Continuous Optimization |
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
In SIAM Conference on Applied Linear Algebra (LA21), 2021.Status: Published
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | SIAM Conference on Applied Linear Algebra (LA21) |
Type of Talk | Minisymposium |
From Data Mining using Tensor Factorizations to Multimodal Data Mining using Coupled Matrix/Tensor Factorizations
In Nordic Probabilistic AI School (virtual), 2021.Status: Published
From Data Mining using Tensor Factorizations to Multimodal Data Mining using Coupled Matrix/Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | Nordic Probabilistic AI School (virtual) |
URL | https://probabilistic.ai/ |
Journal Article
Multi-Linear Population Analysis (MLPA) of LFP Data Using Tensor Decompositions
Frontiers in Applied Mathematics and Statistics 6 (2020).Status: Published
Multi-Linear Population Analysis (MLPA) of LFP Data Using Tensor Decompositions
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2020 |
Journal | Frontiers in Applied Mathematics and Statistics |
Volume | 6 |
Number | 41 |
Date Published | Aug-09-2020 |
Publisher | Frontiers |
Keywords | CANDECOMP/PARAFAC, independent component analysis (ICA), local field potential (LFP), Neuroscience, population rate model, principal component analysis (PCA), tensor decompositions |
URL | https://www.frontiersin.org/article/10.3389/fams.2020.00041/fullhttps://... |
DOI | 10.3389/fams.2020.00041 |
Department of Data Science and Knowledge Discovery
Department of Data Science and Knowledge Discovery (DataSci) aims at advancing frontiers of machine learning and data mining by developing novel methodologies and algorithmic solutions for the analysis of high-dimensional data in science and industry.
Machine learning and data science have gained enormous international momentum, and it has been defined as a separate research topic at Simula since 2018. In particular, as a part of Simula Metropolitan Center for Digital Engineering, Data Science and Knowledge Discovery Department (DataSci) - previously known as the Machine Intelligence Department - was established in 2018.
DataSci at SimulaMet focuses on developing novel data mining/machine learning methods for the analysis of heterogeneous incomplete data (e.g., multi-modal, static, time-evolving, with missing entries) collected from complex systems (e.g., brain, human metabolome), with the goal of revealing interpretable patterns that can lead to improved understanding of such systems. Research activities at DataSci span the following areas: low-rank approximations, multimodal data mining (data fusion, coupled matrix/tensor factorizations), temporal data mining, numerical linear algebra, multilinear algebra, algorithms (numerical optimization) - with applications in precision medicine, phenotyping, omics data analysis, and neuroimaging data analysis (fMRI, EEG, dynamic brain connectivity, multimodal neuroimaging data analysis).
Publications for Department of Data Science and Knowledge Discovery
Proceedings, refereed
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
In Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development. Springer, 2022.Status: Published
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
Afilliation | Machine Learning |
Project(s) | DeCipher, Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development |
Pagination | 94--110 |
Publisher | Springer |
DOI | 10.1007/978-3-031-17030-0_8 |
Multi-task FMRI Data Fusion using IVA and PARAFAC2
In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.Status: Published
Multi-task FMRI Data Fusion using IVA and PARAFAC2
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Pagination | 1466-1470 |
Publisher | IEEE |
DOI | 10.1109/ICASSP43922.2022.9747662 |
Public outreach
Hjerneforskningens matematiske verktøy
Realfagsdagene, 2022.Status: Published
Hjerneforskningens matematiske verktøy
Hva har hjernesignaler og Netflix-likes til felles? Og hvordan hente underliggende mønstre fra tabeller med data? Svarene får du i dette foredraget om tall, faktorisering og hjerneforskning.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Public outreach |
Year of Publication | 2022 |
Publisher | Realfagsdagene |
Talks, contributed
Fully Constrained PARAFAC2 with AO-ADMM
In SIAM Conference on Parallel Processing for Scientific Computing, 2022.Status: Published
Fully Constrained PARAFAC2 with AO-ADMM
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | SIAM Conference on Parallel Processing for Scientific Computing |
An AO-ADMM approach to constrained PARAFAC2
In Nordic AI Meet, 2022.Status: Published
An AO-ADMM approach to constrained PARAFAC2
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Nordic AI Meet |
Characterizing postprandial metabolomics response using multi-way data analysis
In Annual NORBIS Conference, 2022.Status: Published
Characterizing postprandial metabolomics response using multi-way data analysis
Analysis of time-resolved postprandial metabolomics data can enhance our knowledge about the human metabolism by providing a better understanding of regulation of subgroups of metabolites (e.g., lipids) and variations in postprandial responses of subgroups of people, with the potential to ultimately advance precision medicine. However, characterizing postprandial metabolomics response and understanding group differences is a challenging task since it requires the analysis of large-scale metabolomics data from a large set of individuals containing measurements of a wide set of metabolites at multiple time points. Such data is in the form of a three-way array: subjects by metabolites by time points. The state-of-the-art analysis methods mainly focus on clustering temporal profiles relying on summaries of the data across subjects or univariate analysis techniques studying one metabolite at a time, and fail to associate subgroups of subjects and subsets of metabolites with the dynamic time profile simultaneously.
In this study, we use NMR (nuclear magnetic resonance) spectroscopy measurements of plasma samples (of over three hundred individuals from the COPSAC2000 cohort) collected at multiple time points during a challenge test. We use a multi-way analysis technique called the CANDECOMP/PARAFAC (CP) model to extract interpretable patterns from the time-resolved data. We compare the analysis of postprandial data, fasting state-corrected data and only fasting state data, and demonstrate the differences between different analysis approaches.
Our results show that the CP model reveals biologically meaningful patterns capturing how certain metabolite groups and their temporal profiles relate to various meta variables, in particular, BMI (body mass index), confirming already known biological knowledge as well as revealing new biological insights.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Annual NORBIS Conference |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In Norwegian Bioinformatics Days, Sundvolden, Norway, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Norwegian Bioinformatics Days, Sundvolden, Norway |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In Nordic Metabolomics 2022, Copenhagen, Denmark, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Nordic Metabolomics 2022, Copenhagen, Denmark |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In NuGOweek 2022 in Spain, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | NuGOweek 2022 in Spain |
A Flexible Framework for Coupled Matrix/Tensor Factorizations
In TRICAP: Three-way methods In Chemistry And Psychology, 2022.Status: Published
A Flexible Framework for Coupled Matrix/Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | TRICAP: Three-way methods In Chemistry And Psychology |
Publications
Proceedings, refereed
A Time-aware Tensor Decomposition for Tracking Evolving Patterns
In MLSP'23: IEEE International Workshop on Machine Learning for Signal Processing. IEEE, 2023.Status: Accepted
A Time-aware Tensor Decomposition for Tracking Evolving Patterns
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2023 |
Conference Name | MLSP'23: IEEE International Workshop on Machine Learning for Signal Processing |
Publisher | IEEE |
PARAFAC2-based coupled Matrix and Tensor Factorizations
In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023.Status: Published
PARAFAC2-based coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2023 |
Conference Name | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Pagination | 1-5 |
Publisher | IEEE |
DOI | 10.1109/ICASSP49357.2023.10094562 |
Journal Article
Analyzing postprandial metabolomics data using multiway models: A simulation study
bioRxiv (2023).Status: Submitted
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2023 |
Journal | bioRxiv |
Publisher | bioRxiv |
URL | https://www.biorxiv.org/content/10.1101/2022.12.19.521154v2 |
DOI | 10.1101/2022.12.19.521154 |
Characterizing human postprandial metabolic response using multiway data analysis
bioRxiv (2023).Status: Submitted
Characterizing human postprandial metabolic response using multiway data analysis
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2023 |
Journal | bioRxiv |
Publisher | biorxiv |
DOI | 10.1101/2023.08.31.555521 |
Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
WIREs Data Mining and Knowledge Discovery 13 (2023).Status: Published
Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , DeCipher |
Publication Type | Journal Article |
Year of Publication | 2023 |
Journal | WIREs Data Mining and Knowledge Discovery |
Volume | 13 |
Number | e1494 |
Publisher | Wiley |
DOI | 10.1002/widm.1494 |
Talks, invited
Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
In Acceleration and Extrapolation Methods, ICERM, Brown University, 2023.Status: Published
Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2023 |
Location of Talk | Acceleration and Extrapolation Methods, ICERM, Brown University |
URL | https://icerm.brown.edu/topical_workshops/tw-23-aem/ |
Extracting Insights from Complex Data: Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
In IPAM Workshop on Explainable AI for the Sciences: Towards Novel Insights, 2023.Status: Published
Extracting Insights from Complex Data: Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2023 |
Location of Talk | IPAM Workshop on Explainable AI for the Sciences: Towards Novel Insights |
URL | http://www.ipam.ucla.edu/abstract/?tid=18155&pcode=XAI2023 |
Talks, contributed
A Flexible Framework for Coupled Matrix/Tensor Factorizations
In TRICAP: Three-way methods In Chemistry And Psychology, 2022.Status: Published
A Flexible Framework for Coupled Matrix/Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | TRICAP: Three-way methods In Chemistry And Psychology |
An AO-ADMM approach to constrained PARAFAC2
In Nordic AI Meet, 2022.Status: Published
An AO-ADMM approach to constrained PARAFAC2
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Nordic AI Meet |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In Norwegian Bioinformatics Days, Sundvolden, Norway, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Norwegian Bioinformatics Days, Sundvolden, Norway |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In Nordic Metabolomics 2022, Copenhagen, Denmark, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Nordic Metabolomics 2022, Copenhagen, Denmark |
Analyzing postprandial metabolomics data using multiway models: A simulation study
In NuGOweek 2022 in Spain, 2022.Status: Published
Analyzing postprandial metabolomics data using multiway models: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | NuGOweek 2022 in Spain |
Characterizing postprandial metabolomics response using multi-way data analysis
In Annual NORBIS Conference, 2022.Status: Published
Characterizing postprandial metabolomics response using multi-way data analysis
Analysis of time-resolved postprandial metabolomics data can enhance our knowledge about the human metabolism by providing a better understanding of regulation of subgroups of metabolites (e.g., lipids) and variations in postprandial responses of subgroups of people, with the potential to ultimately advance precision medicine. However, characterizing postprandial metabolomics response and understanding group differences is a challenging task since it requires the analysis of large-scale metabolomics data from a large set of individuals containing measurements of a wide set of metabolites at multiple time points. Such data is in the form of a three-way array: subjects by metabolites by time points. The state-of-the-art analysis methods mainly focus on clustering temporal profiles relying on summaries of the data across subjects or univariate analysis techniques studying one metabolite at a time, and fail to associate subgroups of subjects and subsets of metabolites with the dynamic time profile simultaneously.
In this study, we use NMR (nuclear magnetic resonance) spectroscopy measurements of plasma samples (of over three hundred individuals from the COPSAC2000 cohort) collected at multiple time points during a challenge test. We use a multi-way analysis technique called the CANDECOMP/PARAFAC (CP) model to extract interpretable patterns from the time-resolved data. We compare the analysis of postprandial data, fasting state-corrected data and only fasting state data, and demonstrate the differences between different analysis approaches.
Our results show that the CP model reveals biologically meaningful patterns capturing how certain metabolite groups and their temporal profiles relate to various meta variables, in particular, BMI (body mass index), confirming already known biological knowledge as well as revealing new biological insights.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | Annual NORBIS Conference |
Fully Constrained PARAFAC2 with AO-ADMM
In SIAM Conference on Parallel Processing for Scientific Computing, 2022.Status: Published
Fully Constrained PARAFAC2 with AO-ADMM
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2022 |
Location of Talk | SIAM Conference on Parallel Processing for Scientific Computing |
Journal Article
An AO-ADMM approach to constraining PARAFAC2 on all modes
SIAM Journal on Mathematics of Data Science 4 (2022): 1191-1222.Status: Published
An AO-ADMM approach to constraining PARAFAC2 on all modes
Analyzing multi-way measurements with variations across one mode of the dataset is a challenge in various fields including data mining, neuroscience and chemometrics. For example, measurements may evolve over time or have unaligned time profiles. The PARAFAC2 model has been successfully used to analyze such data by allowing the underlying factor matrices in one mode (i.e., the evolving mode) to change across slices. The traditional approach to fit a PARAFAC2 model is to use an alternating least squares-based algorithm, which handles the constant cross-product constraint of the PARAFAC2 model by implicitly estimating the evolving factor matrices. This approach makes imposing regularization on these factor matrices challenging. There is currently no algorithm to flexibly impose such regularization with general penalty functions and hard constraints. In order to address this challenge and to avoid the implicit estimation, in this paper, we propose an algorithm for fitting PARAFAC2 based on alternating optimization with the alternating direction method of multipliers (AO-ADMM). With numerical experiments on simulated data, we show that the proposed PARAFAC2 AO-ADMM approach allows for flexible constraints, recovers the underlying patterns accurately, and is computationally efficient compared to the state-of-the-art. We also apply our model to a real-world chromatography dataset, and show that constraining the evolving mode improves the interpretability of the extracted patterns.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | SIAM Journal on Mathematics of Data Science |
Volume | 4 |
Number | 3 |
Pagination | 1191-1222 |
Publisher | SIAM |
Place Published | SIAM Journal on Mathematics of Data Science |
DOI | 10.1137/21M1450033 |
Exploring Dynamic Metabolomics Data With Multiway Data Analysis: a Simulation Study
BMC Bioinformatics 23 (2022).Status: Published
Exploring Dynamic Metabolomics Data With Multiway Data Analysis: a Simulation Study
Background: Analysis of dynamic metabolomics data holds the promise to improve our understanding of underlying mechanisms in metabolism. For example, it may detect changes in metabolism due to the onset of a disease. Dynamic or time-resolved metabolomics data can be arranged as a three-way array with entries organized according to a subjects mode, a metabolites mode and a time mode. While such time-evolving multiway data sets are increasingly collected, revealing the underlying mechanisms and their dynamics from such data remains challenging. For such data, one of the complexities is the presence of a superposition of several sources of variation: induced variation (due to experimental conditions or inborn errors), individual variation, and measurement error. Multiway data analysis (also known as tensor factorizations) has been successfully used in data mining to find the underlying patterns in multiway data. In this paper, we study the use of multiway data analysis to reveal the underlying patterns and dynamics in time-resolved metabolomics data.
Results: We focus on simulated data arising from different dynamic models of increasing complexity, i.e., a simple linear system, a yeast glycolysis model, and a human cholesterol model. We generate data with induced variation as well as individual variation. Systematic experiments are performed to demonstrate the advantages and limitations of multiway data analysis in analyzing such dynamic metabolomics data and their capacity to disentangle the different sources of variations. We choose to use simulations since we want to understand the capability of multiway data analysis methods which is facilitated by knowing the ground truth.
Conclusion: Our numerical experiments demonstrate that despite the increasing complexity of the studied dynamic metabolic models, tensor factorization methods CANDECOMP/PARAFAC(CP) and Parallel Profiles with Linear Dependences (Paralind) can disentangle the sources of variations and thereby reveal the underlying mechanisms and their dynamics.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | BMC Bioinformatics |
Volume | 23 |
Number | Article 31 |
Date Published | 2022 |
Publisher | Springer |
DOI | 10.1186/s12859-021-04550-5 |
Modeling Variation in Mobile Download Speed in Presence of Missing Samples
IEEE Transactions on Mobile Computing (2022): 1-16.Status: Published
Modeling Variation in Mobile Download Speed in Presence of Missing Samples
Afilliation | Communication Systems, Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | IEEE Transactions on Mobile Computing |
Pagination | 1 - 16 |
Publisher | IEEE |
ISSN | 1536-1233 |
URL | https://ieeexplore.ieee.org/document/9999262/http://xplorestaging.ieee.o... |
DOI | 10.1109/TMC.2022.3231928 |
Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness
IEEE Signal Processing Magazine 39, no. 4 (2022): 8-24.Status: Published
Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | IEEE Signal Processing Magazine |
Volume | 39 |
Issue | 4 |
Pagination | 8-24 |
Date Published | 06/2022 |
Publisher | IEEE |
DOI | 10.1109/MSP.2022.3163870 |
Tracing Evolving Networks using Tensor Factorizations vs. ICA-based Approaches
Frontiers in Neuroscience 16 (2022).Status: Published
Tracing Evolving Networks using Tensor Factorizations vs. ICA-based Approaches
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2022 |
Journal | Frontiers in Neuroscience |
Volume | 16 |
Date Published | 04/2022 |
Publisher | Frontiers |
URL | https://www.frontiersin.org/article/10.3389/fnins.2022.861402 |
DOI | 10.3389/fnins.2022.861402 |
Poster
Characterizing postprandial metabolic response using multi-way data analysis
Norwegian Bioinformatics Days, 2022.Status: Published
Characterizing postprandial metabolic response using multi-way data analysis
Analysis of time-resolved postprandial metabolomics data can enhance our knowledge about the human metabolism by providing a better understanding of regulation of subgroups of metabolites (e.g., lipids) and variations in postprandial responses of subgroups of people, with the potential to ultimately advance precision medicine. However, characterizing postprandial metabolomics response and understanding group differences is a challenging task since it requires the analysis of large-scale metabolomics data from a large set of individuals containing measurements of a wide set of metabolites at multiple time points. Such data is in the form of a three-way array: subjects by metabolites by time points. The state-of-the-art analysis methods mainly focus on clustering temporal profiles relying on summaries of the data across subjects or univariate analysis techniques studying one metabolite at a time, and fail to associate subgroups of subjects and subsets of metabolites with the dynamic time profile simultaneously.
In this study, we use NMR (nuclear magnetic resonance) spectroscopy measurements of plasma samples (of over three hundred individuals from the COPSAC2000 cohort) collected at multiple time points during a challenge test. We use a multi-way analysis technique called the CANDECOMP/PARAFAC (CP) model to extract interpretable patterns from the time-resolved data. We compare the analysis of postprandial data, fasting state-corrected data and only fasting state data, and demonstrate the differences between different analysis approaches.
Our results show that the CP model reveals biologically meaningful patterns capturing how certain metabolite groups and their temporal profiles relate to various meta variables, in particular, BMI (body mass index), confirming already known biological knowledge as well as revealing new biological insights.
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Poster |
Year of Publication | 2022 |
Place Published | Norwegian Bioinformatics Days |
Keywords | CANDECOMP/PARAFAC, Dynamic metabolomics data, large-scale dataset, Tensor factorization |
Revealing dynamic changes in metabolism through the analysis of postprandial metabolomics data: A simulation study
Metabolomics 2022, Valencia, Spain, 2022.Status: Published
Revealing dynamic changes in metabolism through the analysis of postprandial metabolomics data: A simulation study
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Poster |
Year of Publication | 2022 |
Place Published | Metabolomics 2022, Valencia, Spain |
Talks, invited
Constrained Multi-Modal Data Mining Using Coupled Matrix and Tensor Factorizations
In SIAM Conference on Mathematics of Data Science, 2022.Status: Published
Constrained Multi-Modal Data Mining Using Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2022 |
Location of Talk | SIAM Conference on Mathematics of Data Science |
Type of Talk | Minisymposium talk |
URL | https://meetings.siam.org/sess/dsp_programsess.cfm?SESSIONCODE=74454 |
Constrained Multimodal Data Mining
In BigInsight Seminar, University of Oslo, Norway, 2022.Status: Published
Constrained Multimodal Data Mining
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2022 |
Location of Talk | BigInsight Seminar, University of Oslo, Norway |
URL | https://www.biginsight.no/events |
Extracting Insights from Complex Data: Data Mining using Tensor Factorizations
In SILS (Swammerdam Institute for Life Sciences) Data Science Symposium, University of Amsterdam, Netherlands, 2022.Status: Published
Extracting Insights from Complex Data: Data Mining using Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2022 |
Location of Talk | SILS (Swammerdam Institute for Life Sciences) Data Science Symposium, University of Amsterdam, Netherlands |
Proceedings, refereed
Multi-task FMRI Data Fusion using IVA and PARAFAC2
In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022.Status: Published
Multi-task FMRI Data Fusion using IVA and PARAFAC2
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Pagination | 1466-1470 |
Publisher | IEEE |
DOI | 10.1109/ICASSP43922.2022.9747662 |
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
In Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development. Springer, 2022.Status: Published
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
Afilliation | Machine Learning |
Project(s) | DeCipher, Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2022 |
Conference Name | Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development |
Pagination | 94--110 |
Publisher | Springer |
DOI | 10.1007/978-3-031-17030-0_8 |
Talks, invited
A Flexible Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorizations based on the Alternating Direction Method of Multipliers
In Europt21, 18th Workshop on Advances in Continuous Optimization, 2021.Status: Published
A Flexible Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorizations based on the Alternating Direction Method of Multipliers
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | Europt21, 18th Workshop on Advances in Continuous Optimization |
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
In SIAM Conference on Applied Linear Algebra (LA21), 2021.Status: Published
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | SIAM Conference on Applied Linear Algebra (LA21) |
Type of Talk | Minisymposium |
From Data Mining using Tensor Factorizations to Multimodal Data Mining using Coupled Matrix/Tensor Factorizations
In Nordic Probabilistic AI School (virtual), 2021.Status: Published
From Data Mining using Tensor Factorizations to Multimodal Data Mining using Coupled Matrix/Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2021 |
Location of Talk | Nordic Probabilistic AI School (virtual) |
URL | https://probabilistic.ai/ |
Talks, contributed
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
In Asilomar Conference on Signals, Systems, and Computers, 2021.Status: Published
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
An effective way of jointly analyzing data from multiple sources is through coupled matrix and tensor factorizations (CMTF). Different characteristics of datasets from multiple sources require to employ various regularizations, constraints, loss functions and different types of coupling structures between datasets. While existing algorithmic approaches for CMTF can incorporate constraints, linear couplings and different loss functions, none of them has been shown to achieve the flexibility to incorporate all. We propose a flexible algorithmic framework for coupled matrix and tensor factorizations, which utilizes Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM). The framework facilitates the use of a variety of constraints, loss functions and couplings with linear transformations. Numerical experiments on simulated datasets and real data from chemometrics and hyperspectral super-resolution demonstrate that the proposed approach is accurate, flexible and computationally efficient with comparable or better performance than available CMTF algorithms.
While we focus on CANDECOMP/PARAFAC (CP) –based CMTF models, we will also briefly discuss the use of an AO-ADMM based algorithmic approach for fitting a PARAFAC2 model. We demonstrate that the proposed algorithmic approach enables imposing constraints in all modes, which has been a challenge using the traditional alternating least squares-based algorithm used for PARAFAC2.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | Asilomar Conference on Signals, Systems, and Computers |
Type of Talk | Invited Session Talk |
Exploring dynamic metabolomics data with multiway data analysis: A simulation study
In Virtual conference. SIAM Conference on Applications of Dynamical Systems, 2021.Status: Published
Exploring dynamic metabolomics data with multiway data analysis: A simulation study
Analysis of dynamic metabolomics data sets holds the promise to improve our understanding of the underlying mechanisms in human metabolism. That is crucial to detect the changes in the metabolism that can potentially lead to diseases. Dynamic metabolomics data has more than two axes of variation, i.e., samples, metabolites and time. While such time-evolving multi-way data sets are collected more and more in recent years, revealing the underlying mechanisms and their dynamics from such data remains challenging.
This talk will focus on a systematic study demonstrating the advantages and limitations of multi-way data analysis (also known as tensor factorizations) in terms of analyzing dynamic metabolomics data. We study different dynamic models of increasing complexity, i.e., a simple linear system, a yeast glycolysis model, a human cholesterol model, and generate data with different types of variation. Our numerical experiments demonstrate that despite the increasing complexity of the studied models, tensor factorization methods CANDECOMP/PARAFAC(CP) and PARAllel Profiles with LINear Dependences (PARALIND) can reveal the underlying mechanisms and their dynamics.
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | Virtual conference |
Publisher | SIAM Conference on Applications of Dynamical Systems |
Generalized Low-Rank Models for Phenotyping Cervical Cancer Risk Groups using Medical Questionnaires
In Stavanger, Norway, 2021.Status: Published
Generalized Low-Rank Models for Phenotyping Cervical Cancer Risk Groups using Medical Questionnaires
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , DeCipher |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | Stavanger, Norway |
Tracing Dynamic Networks through Constrained Parafac2 Decomposition
In SIAM Conference on Applied Linear Algebra (LA21), Virtual Conference. SIAM, 2021.Status: Published
Tracing Dynamic Networks through Constrained Parafac2 Decomposition
Time-evolving data analysis is crucial for understanding complex systems such as the brain. Methods that assume static networks have successfully recovered spatial networks of connectivity from neuroimaging data. Still, discovering both underlying networks and their evolution is a challenging task.
To capture temporal evolution of connectivity networks, we arrange dynamic data as a tensor and use a tensor factorization method called PARAFAC2. PARAFAC2 deciphers the hidden structure of dynamic networks and yields unique and interpretable components. Preliminary results using PARAFAC2 in neuroimaging data analysis are promising. However, the constant cross-product constraint on the time-evolving mode hinders the use of additional constraints or regularization (e.g. spatial smoothness) on this mode. Currently, the only way to regularize the time-evolving mode of a PARAFAC2 model is with a flexible coupling approach, which finds the solution through regularized least-squares subproblems. Instead, we use an alternating direction method of multipliers (ADMM) based approach to widen the possible regularization penalties to any proximable function.
Our numerical experiments demonstrate that the proposed ADMM-based algorithmic approach for PARAFAC2 can accurately recover the underlying evolving components, is flexible in terms of imposing constraints and also computationally efficient.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, contributed |
Year of Publication | 2021 |
Location of Talk | SIAM Conference on Applied Linear Algebra (LA21), Virtual Conference |
Publisher | SIAM |
Journal Article
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
IEEE Journal of Selected Topics in Signal Processing 15, no. 3 (2021): 506-521.Status: Published
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2021 |
Journal | IEEE Journal of Selected Topics in Signal Processing |
Volume | 15 |
Issue | 3 |
Pagination | 506 - 521 |
Publisher | IEEE |
DOI | 10.1109/JSTSP.2020.3045848 |
Poster
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, 2021.Status: Published
An Optimization Framework for Regularized Linearly Coupled Matrix-Tensor Factorization
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Poster |
Year of Publication | 2021 |
Place Published | 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands |
Proceedings, refereed
PARAFAC2 AO-ADMM: Constraints in all modes
In 2021 29th European Signal Processing Conference (EUSIPCO). IEEE, 2021.Status: Published
PARAFAC2 AO-ADMM: Constraints in all modes
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Proceedings, refereed |
Year of Publication | 2021 |
Conference Name | 2021 29th European Signal Processing Conference (EUSIPCO) |
Pagination | 1040-1044 |
Publisher | IEEE |
Proceedings, refereed
An Optimization Framework for RegularizedLinearly Coupled Matrix-Tensor Factorization
In European Signal Processing Conference (EUSIPCO). IEEE, 2020.Status: Published
An Optimization Framework for RegularizedLinearly Coupled Matrix-Tensor Factorization
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2020 |
Conference Name | European Signal Processing Conference (EUSIPCO) |
Pagination | 985-989 |
Publisher | IEEE |
URL | https://www.eurasip.org/Proceedings/Eusipco/Eusipco2020/pdfs/0000985.pdf |
Tracing Network Evolution Using The Parafac2 Model
In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona, Spain: IEEE, 2020.Status: Published
Tracing Network Evolution Using The Parafac2 Model
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2020 |
Conference Name | 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Publisher | IEEE |
Place Published | Barcelona, Spain |
URL | https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=9040208http... |
DOI | 10.1109/ICASSP40776.202010.1109/ICASSP40776.2020.9053902 |
Journal Article
Cross-product penalized component analysis (X-CAN)
Chemometrics and Intelligent Laboratory Systems 203 (2020): 104038.Status: Published
Cross-product penalized component analysis (X-CAN)
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2020 |
Journal | Chemometrics and Intelligent Laboratory Systems |
Volume | 203 |
Pagination | 104038 |
Date Published | 06/2020 |
Publisher | Elsevier |
ISSN | 01697439 |
DOI | 10.1016/j.chemolab.2020.104038 |
Multi-Linear Population Analysis (MLPA) of LFP Data Using Tensor Decompositions
Frontiers in Applied Mathematics and Statistics 6 (2020).Status: Published
Multi-Linear Population Analysis (MLPA) of LFP Data Using Tensor Decompositions
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Journal Article |
Year of Publication | 2020 |
Journal | Frontiers in Applied Mathematics and Statistics |
Volume | 6 |
Number | 41 |
Date Published | Aug-09-2020 |
Publisher | Frontiers |
Keywords | CANDECOMP/PARAFAC, independent component analysis (ICA), local field potential (LFP), Neuroscience, population rate model, principal component analysis (PCA), tensor decompositions |
URL | https://www.frontiersin.org/article/10.3389/fams.2020.00041/fullhttps://... |
DOI | 10.3389/fams.2020.00041 |
Talks, invited
Multi Modal Data Mining using Coupled Matrix/Tensor Factorizations
In Tufts University - TRIPODS Seminar (virtual), 2020.Status: Published
Multi Modal Data Mining using Coupled Matrix/Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
Publication Type | Talks, invited |
Year of Publication | 2020 |
Location of Talk | Tufts University - TRIPODS Seminar (virtual) |
URL | https://tripods.tufts.edu/about/events/multi-modal-data-mining-using-cou... |
Book Chapter
Multilinear Models, Iterative Methods
In Comprehensive Chemometrics (Second Edition), 267-304. Chemical and Biochemical Data Analysis. Elsevier, 2020.Status: Published
Multilinear Models, Iterative Methods
In this section, multilinear models for multi-way arrays requiring iterative fitting algorithms are outlined. Among them: the PARAFAC (PARAllel FACtor analysis) model and one of its variants (the PARAFAC2 model); Tucker models in which one or more modes are reduced (viz., the N-way Tucker-N and Tucker-m models); hybrid models having intermediate properties between PARAFAC and Tucker ones; and coupled matrix and tensor decompositions (CMTF) which simultaneously decomposes multiple tensors. Five examples are included as to illustrate some practical aspects concerning the use of these models on analytical data.
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Book Chapter |
Year of Publication | 2020 |
Book Title | Comprehensive Chemometrics (Second Edition) |
Secondary Title | Chemical and Biochemical Data Analysis |
Pagination | 267-304 |
Publisher | Elsevier |
ISBN Number | 978-0-12-409547-2 |
Keywords | -way Tucker models, CANDECOMP, Curve resolution, Exploratory analysis, Least squares, Linked mode PARAFAC, Multi-way analysis, Multi-way array, Multilinear model, PARAFAC, PARAFAC2, PARALIND, Restricted Tucker models, Tensor decomposition, Tensor-matrix factorization |
URL | http://www.sciencedirect.com/science/article/pii/B9780124095472146098 |
DOI | 10.1016/B978-0-12-409547-2.14609-8 |
Talks, invited
Biomarker Discovery through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data
In IEEE EMBC (Engineering in Medicine and Biology Conference), Berlin, Germany, 2019.Status: Published
Biomarker Discovery through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2019 |
Location of Talk | IEEE EMBC (Engineering in Medicine and Biology Conference), Berlin, Germany |
Type of Talk | Invited Session Paper |
Unraveling Biomarkers through Multi-Modal Data Fusion
In IEEE ISMICT (International Symposium on Medical Information and Communication Technology), Oslo, Norway, 2019.Status: Published
Unraveling Biomarkers through Multi-Modal Data Fusion
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2019 |
Location of Talk | IEEE ISMICT (International Symposium on Medical Information and Communication Technology), Oslo, Norway |
Type of Talk | Invited |
Unraveling Interpretable Patterns through Data Fusion based on Coupled Matrix and Tensor Factorizations
In AI and Tensor Factorizations for Physical, Chemical, and Biological Systems, Santa Fe, NM, USA, 2019.Status: Published
Unraveling Interpretable Patterns through Data Fusion based on Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2019 |
Location of Talk | AI and Tensor Factorizations for Physical, Chemical, and Biological Systems, Santa Fe, NM, USA |
Type of Talk | Invited |
Unraveling Interpretable Patterns through Data Fusion based on Coupled Matrix and Tensor Factorizations
In KDD Workshop on Tensor Methods for Emerging Data Science Challenges, Anchorage, Alaska, USA, 2019.Status: Published
Unraveling Interpretable Patterns through Data Fusion based on Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2019 |
Location of Talk | KDD Workshop on Tensor Methods for Emerging Data Science Challenges, Anchorage, Alaska, USA |
Type of Talk | Keynote |
Journal Article
Biomarkers of individual foods, and separation of diets using untargeted LC-MS based plasma metabolomics in a randomized controlled trial
Molecular Nutrition & Food Research 63 (2019): 1-10.Status: Published
Biomarkers of individual foods, and separation of diets using untargeted LC-MS based plasma metabolomics in a randomized controlled trial
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2019 |
Journal | Molecular Nutrition & Food Research |
Volume | 63 |
Number | 1800215 |
Pagination | 1-10 |
Publisher | Wiley |
DOI | 10.1002/mnfr.201800215 |
Unraveling Diagnostic Biomarkers of Schizophrenia Through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data
Frontiers in Neuroscience 13 (2019).Status: Published
Unraveling Diagnostic Biomarkers of Schizophrenia Through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2019 |
Journal | Frontiers in Neuroscience |
Volume | 13 |
Date Published | Mar-05-2019 |
Publisher | Frontiers |
DOI | 10.3389/fnins.2019.00416 |
Proceedings, refereed
Multiway Reliability Analysis of Mobile Broadband Networks
In the Internet Measurement ConferenceProceedings of the Internet Measurement Conference on - IMC '19. New York, NY, USA: ACM Press, 2019.Status: Published
Multiway Reliability Analysis of Mobile Broadband Networks
Afilliation | Communication Systems, Machine Learning |
Project(s) | The Center for Resilient Networks and Applications, Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2019 |
Conference Name | the Internet Measurement ConferenceProceedings of the Internet Measurement Conference on - IMC '19 |
Pagination | 358-364 |
Publisher | ACM Press |
Place Published | New York, NY, USA |
ISBN Number | 9781450369480 |
URL | http://dl.acm.org/citation.cfm?doid=3355369http://dl.acm.org/citation.cf... |
DOI | 10.1145/335536910.1145/3355369.3355591 |
Talks, invited
Data Fusion based on Coupled Matrix and Tensor Factorizations
In 5th Conference on Constraint-Based Reconstruction and Analysis (COBRA 2018), Seattle, USA, 2018.Status: Published
Data Fusion based on Coupled Matrix and Tensor Factorizations
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2018 |
Location of Talk | 5th Conference on Constraint-Based Reconstruction and Analysis (COBRA 2018), Seattle, USA |
URL | https://www.aiche.org/sbe/conferences/conference-on-constraint-based-rec... |
Tutorial on Tensor Factorizations, Data Fusion & Applications
In 14th International Conference on Latent Variable Analysis and Signal Separation, Guildford, UK, 2018.Status: Published
Tutorial on Tensor Factorizations, Data Fusion & Applications
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, invited |
Year of Publication | 2018 |
Location of Talk | 14th International Conference on Latent Variable Analysis and Signal Separation, Guildford, UK |
Type of Talk | Tutorial |
URL | http://cvssp.org/events/lva-ica-2018/tutorials/ |
Talks, contributed
Structure-Revealing Data Fusion Models based on Coupled Matrix and Tensor Factorizations and Their Applications
In Three‐way Methods in Chemistry and Psychology (TRICAP), New Mexico, USA, 2018.Status: Published
Structure-Revealing Data Fusion Models based on Coupled Matrix and Tensor Factorizations and Their Applications
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2018 |
Location of Talk | Three‐way Methods in Chemistry and Psychology (TRICAP), New Mexico, USA |
URL | https://www.sandia.gov/tricap2018/Home.html |
Structure-Revealing Data Fusion Models based on Coupled Matrix and Tensor Factorizations and Their Applications
In TRICAP: Three-way methods In Chemistry And Psychology, 2018.Status: Published
Structure-Revealing Data Fusion Models based on Coupled Matrix and Tensor Factorizations and Their Applications
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Talks, contributed |
Year of Publication | 2018 |
Location of Talk | TRICAP: Three-way methods In Chemistry And Psychology |
Journal Article
The molecular fingerprint of fluorescent natural organic matter offers insight into biogeochemical sources and diagenetic state
Analytical Chemistry 90, no. 24 (2018): 14188-14197.Status: Published
The molecular fingerprint of fluorescent natural organic matter offers insight into biogeochemical sources and diagenetic state
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2018 |
Journal | Analytical Chemistry |
Volume | 90 |
Issue | 24 |
Pagination | 14188–14197 |
Publisher | ACS |
ISSN | 0003-2700 |
URL | http://pubs.acs.org/doi/10.1021/acs.analchem.8b02863http://pubs.acs.org/... |
DOI | 10.1021/acs.analchem.8b02863 |
Proceedings, refereed
ACMTF for Fusion of Multi-Modal Neuroimaging Data and Identification of Biomarkers
In EUSIPCO 2017: Proceedings of the 25th European Signal Processing Conference. IEEE, 2017.Status: Published
ACMTF for Fusion of Multi-Modal Neuroimaging Data and Identification of Biomarkers
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2017 |
Conference Name | EUSIPCO 2017: Proceedings of the 25th European Signal Processing Conference |
Publisher | IEEE |
DOI | 10.23919/EUSIPCO.2017.8081286 |
Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia
In ISCAS 2017: Proceedings of IEEE International Symposium on Circuits and Systems. IEEE, 2017.Status: Published
Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Proceedings, refereed |
Year of Publication | 2017 |
Conference Name | ISCAS 2017: Proceedings of IEEE International Symposium on Circuits and Systems |
Pagination | 314-317 |
Publisher | IEEE |
DOI | 10.1109/ISCAS.2017.8050303 |
Journal Article
Common and distinct components in data fusion
Journal of Chemometrics 31, no. 7 (2017): e2900.Status: Published
Common and distinct components in data fusion
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2017 |
Journal | Journal of Chemometrics |
Volume | 31 |
Issue | 7 |
Pagination | e2900 |
Date Published | Jan-07-2017 |
Publisher | Wiley |
URL | http://doi.wiley.com/10.1002/cem.v31.7http://doi.wiley.com/10.1002/cem.2... |
DOI | 10.1002/cem.v31.710.1002/cem.2900 |
Forecasting Chronic Diseases Using Data Fusion
Journal of Proteome Research 16, no. 7 (2017): 2435-2444.Status: Published
Forecasting Chronic Diseases Using Data Fusion
Afilliation | Machine Learning |
Project(s) | Department of Data Science and Knowledge Discovery |
Publication Type | Journal Article |
Year of Publication | 2017 |
Journal | Journal of Proteome Research |
Volume | 16 |
Issue | 7 |
Pagination | 2435 - 2444 |
Date Published | Jul-07-2017 |
Publisher | ACS |
ISSN | 1535-3893 |
URL | http://pubs.acs.org/doi/10.1021/acs.jproteome.7b00039http://pubs.acs.org... |
DOI | 10.1021/acs.jproteome.7b00039 |