Steven Gardner, Oleg Golovidov, J. Griffin, P. Koch, W. Thompson, B. Wujek, Yan Xu
Automated machine learning has gained a lot of attention recently. Building and selecting the right machine learning models is often a multi-objective optimization problem. General purpose machine learning software that simultaneously supports multiple objectives and constraints is scant, though the potential benefits are great. In this work, we present a framework called Autotune that effectively handles multiple objectives and constraints that arise in machine learning problems. Autotune is built on a suite of derivative-free optimization methods, and utilizes multi-level parallelism in a distributed computing environment for automatically training, scoring, and selecting good models. Incorporation of multiple objectives and constraints in the model exploration and selection process provides the flexibility needed to satisfy trade-offs necessary in practical machine learning applications. Experimental results from standard multi-objective optimization benchmark problems show that Autotune is very efficient in capturing Pareto fronts. These benchmark results also show how adding constraints can guide the search to more promising regions of the solution space, ultimately producing more desirable Pareto fronts. Results from two real-world case studies demonstrate the effectiveness of the constrained multi-objective optimization capability offered by Autotune.
{"title":"Constrained Multi-Objective Optimization for Automated Machine Learning","authors":"Steven Gardner, Oleg Golovidov, J. Griffin, P. Koch, W. Thompson, B. Wujek, Yan Xu","doi":"10.1109/DSAA.2019.00051","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00051","url":null,"abstract":"Automated machine learning has gained a lot of attention recently. Building and selecting the right machine learning models is often a multi-objective optimization problem. General purpose machine learning software that simultaneously supports multiple objectives and constraints is scant, though the potential benefits are great. In this work, we present a framework called Autotune that effectively handles multiple objectives and constraints that arise in machine learning problems. Autotune is built on a suite of derivative-free optimization methods, and utilizes multi-level parallelism in a distributed computing environment for automatically training, scoring, and selecting good models. Incorporation of multiple objectives and constraints in the model exploration and selection process provides the flexibility needed to satisfy trade-offs necessary in practical machine learning applications. Experimental results from standard multi-objective optimization benchmark problems show that Autotune is very efficient in capturing Pareto fronts. These benchmark results also show how adding constraints can guide the search to more promising regions of the solution space, ultimately producing more desirable Pareto fronts. Results from two real-world case studies demonstrate the effectiveness of the constrained multi-objective optimization capability offered by Autotune.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122501158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Uplift modeling is an emerging machine learning approach for estimating the treatment effect at an individual or subgroup level. It can be used for optimizing the performance of interventions such as marketing campaigns and product designs. Uplift modeling can be used to estimate which users are likely to benefit from a treatment and then prioritize delivering or promoting the preferred experience to those users. An important but so far neglected use case for uplift modeling is an experiment with multiple treatment groups that have different costs, such as for example when different communication channels and promotion types are tested simultaneously. In this paper, we extend standard uplift models to support multiple treatment groups with different costs. We evaluate the performance of the proposed models using both synthetic and real data. We also describe a production implementation of the approach.
{"title":"Uplift Modeling for Multiple Treatments with Cost Optimization","authors":"Zhenyu Zhao, Totte Harinen","doi":"10.1109/dsaa.2019.00057","DOIUrl":"https://doi.org/10.1109/dsaa.2019.00057","url":null,"abstract":"Uplift modeling is an emerging machine learning approach for estimating the treatment effect at an individual or subgroup level. It can be used for optimizing the performance of interventions such as marketing campaigns and product designs. Uplift modeling can be used to estimate which users are likely to benefit from a treatment and then prioritize delivering or promoting the preferred experience to those users. An important but so far neglected use case for uplift modeling is an experiment with multiple treatment groups that have different costs, such as for example when different communication channels and promotion types are tested simultaneously. In this paper, we extend standard uplift models to support multiple treatment groups with different costs. We evaluate the performance of the proposed models using both synthetic and real data. We also describe a production implementation of the approach.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128131680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mojtaba Sedigh Fazli, Rachel V. Stadler, BahaaEddin AlAila, S. Vella, S. Moreno, G. Ward, Shannon P. Quinn
Tracking cell particles in 3D microscopy videos is a challenging task but is of great significance for modeling the motion of cells. Proper characterization of the cell's shape, evolution, and their movement over time is crucial to understanding and modeling the mechanobiology of cell migration in many diseases. One in particular, toxoplasmosis is the disease caused by the parasite Toxoplasma gondii. Roughly, one-third of the world's population tests positive for T. gondii. Its virulence is linked to its lytic cycle, predicated on its motility and ability to enter and exit nucleated cells; therefore, studies elucidating its motility patterns are critical to the eventual development of therapeutic strategies. Here, we present a computational framework for fast and scalable detection, tracking, and identification of T. gondii motion phenotypes in 3D videos, in a completely unsupervised fashion. Our pipeline consists of several different modules including preprocessing, sparsification, cell detection, cell tracking, trajectories extraction, parametrization of the trajectories; and finally, a clustering step. Additionally, we identified the computational bottlenecks, and developed a lightweight and highly scalable pipeline through a combination of task distribution and parallelism. Our results prove both the accuracy and performance of our method.
{"title":"Lightweight and Scalable Particle Tracking and Motion Clustering of 3D Cell Trajectories","authors":"Mojtaba Sedigh Fazli, Rachel V. Stadler, BahaaEddin AlAila, S. Vella, S. Moreno, G. Ward, Shannon P. Quinn","doi":"10.1109/DSAA.2019.00056","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00056","url":null,"abstract":"Tracking cell particles in 3D microscopy videos is a challenging task but is of great significance for modeling the motion of cells. Proper characterization of the cell's shape, evolution, and their movement over time is crucial to understanding and modeling the mechanobiology of cell migration in many diseases. One in particular, toxoplasmosis is the disease caused by the parasite Toxoplasma gondii. Roughly, one-third of the world's population tests positive for T. gondii. Its virulence is linked to its lytic cycle, predicated on its motility and ability to enter and exit nucleated cells; therefore, studies elucidating its motility patterns are critical to the eventual development of therapeutic strategies. Here, we present a computational framework for fast and scalable detection, tracking, and identification of T. gondii motion phenotypes in 3D videos, in a completely unsupervised fashion. Our pipeline consists of several different modules including preprocessing, sparsification, cell detection, cell tracking, trajectories extraction, parametrization of the trajectories; and finally, a clustering step. Additionally, we identified the computational bottlenecks, and developed a lightweight and highly scalable pipeline through a combination of task distribution and parallelism. Our results prove both the accuracy and performance of our method.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130334538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm works the best on a particular problem. We believe that the two crucial steps of MCS - base classifier generation and multiple classifier combination, need to be designed coordinately to produce robust results. In this work, we show that for different testing instances, better classifiers may be trained from different subdomains of training instances including, for example, neighboring instances of the testing instance, or even instances far away from the testing instance. To utilize this intuition, we propose Individualized Classifier Ensemble (ICE). ICE groups training data into overlapping clusters, builds a classifier for each cluster, and then associates each training instance to the top-performing models while taking into account model types and frequency. In testing, ICE finds the k most similar training instances for a testing instance, then predicts class label of the testing instance by averaging the prediction from models associated with these training instances. Evaluation results on 49 benchmarks show that ICE has a stable improvement on a significant proportion of datasets over existing MCS methods. ICE provides a novel choice of utilizing internal patterns among instances to improve classification, and can be easily combined with various classification models and applied to many application domains.
{"title":"A Novel Multiple Classifier Generation and Combination Framework Based on Fuzzy Clustering and Individualized Ensemble Construction","authors":"Zhenzhu Gao, Maryam Zand, Jianhua Ruan","doi":"10.1109/DSAA.2019.00038","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00038","url":null,"abstract":"Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm works the best on a particular problem. We believe that the two crucial steps of MCS - base classifier generation and multiple classifier combination, need to be designed coordinately to produce robust results. In this work, we show that for different testing instances, better classifiers may be trained from different subdomains of training instances including, for example, neighboring instances of the testing instance, or even instances far away from the testing instance. To utilize this intuition, we propose Individualized Classifier Ensemble (ICE). ICE groups training data into overlapping clusters, builds a classifier for each cluster, and then associates each training instance to the top-performing models while taking into account model types and frequency. In testing, ICE finds the k most similar training instances for a testing instance, then predicts class label of the testing instance by averaging the prediction from models associated with these training instances. Evaluation results on 49 benchmarks show that ICE has a stable improvement on a significant proportion of datasets over existing MCS methods. ICE provides a novel choice of utilizing internal patterns among instances to improve classification, and can be easily combined with various classification models and applied to many application domains.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122997637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Cook, Bappaditya Mandal, Donna Berry, Matthew Johnson
Autism spectrum disorders (ASD) impact the cognitive, social, communicative and behavioral abilities of an individual. The development of new clinical decision support systems is of importance in reducing the delay between presentation of symptoms and an accurate diagnosis. In this work, we contribute a new database consisting of video clips of typical (normal) and atypical (such as hand flapping, spinning or rocking) behaviors, displayed in natural settings, which have been collected from the YouTube video website. We propose a preliminary non-intrusive approach based on skeleton keypoint identification using pretrained deep neural networks on human body video clips to extract features and perform body movement analysis that differentiates typical and atypical behaviors of children. Experimental results on the newly contributed database show that our platform performs best with decision tree as the classifier when compared to other popular methodologies and offers a baseline against which alternate approaches may developed and tested.
{"title":"Towards Automatic Screening of Typical and Atypical Behaviors in Children With Autism","authors":"A. Cook, Bappaditya Mandal, Donna Berry, Matthew Johnson","doi":"10.1109/DSAA.2019.00065","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00065","url":null,"abstract":"Autism spectrum disorders (ASD) impact the cognitive, social, communicative and behavioral abilities of an individual. The development of new clinical decision support systems is of importance in reducing the delay between presentation of symptoms and an accurate diagnosis. In this work, we contribute a new database consisting of video clips of typical (normal) and atypical (such as hand flapping, spinning or rocking) behaviors, displayed in natural settings, which have been collected from the YouTube video website. We propose a preliminary non-intrusive approach based on skeleton keypoint identification using pretrained deep neural networks on human body video clips to extract features and perform body movement analysis that differentiates typical and atypical behaviors of children. Experimental results on the newly contributed database show that our platform performs best with decision tree as the classifier when compared to other popular methodologies and offers a baseline against which alternate approaches may developed and tested.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116103403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arindam Paul, M. Mozaffar, Zijiang Yang, W. Liao, A. Choudhary, Jian Cao, Ankit Agrawal
Additive Manufacturing (AM) is a manufacturing paradigm that builds three-dimensional objects from a computer-aided design model by successively adding material layer by layer. AM has become very popular in the past decade due to its utility for fast prototyping such as 3D printing as well as manufacturing functional parts with complex geometries using processes such as laser metal deposition that would be difficult to create using traditional machining. As the process for creating an intricate part for an expensive metal such as Titanium is prohibitive with respect to cost, computational models are used to simulate the behavior of AM processes before the experimental run. However, as the simulations are computationally costly and time-consuming for predicting multiscale multi-physics phenomena in AM, physics-informed data-driven machine-learning systems for predicting the behavior of AM processes are immensely beneficial. Such models accelerate not only multiscale simulation tools but also empower real-time control systems using in-situ data. In this paper, we design and develop essential components of a scientific framework for developing a data-driven model-based real-time control system. Finite element methods are employed for solving time-dependent heat equations and developing the database. The proposed framework uses extremely randomized trees - an ensemble of bagged decision trees as the regression algorithm iteratively using temperatures of prior voxels and laser information as inputs to predict temperatures of subsequent voxels. The models achieve mean absolute percentage errors below 1% for predicting temperature profiles for AM processes. The code is made available for the research community at https://github.com/paularindam/ml-iter-additive.
{"title":"A Real-Time Iterative Machine Learning Approach for Temperature Profile Prediction in Additive Manufacturing Processes","authors":"Arindam Paul, M. Mozaffar, Zijiang Yang, W. Liao, A. Choudhary, Jian Cao, Ankit Agrawal","doi":"10.1109/DSAA.2019.00069","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00069","url":null,"abstract":"Additive Manufacturing (AM) is a manufacturing paradigm that builds three-dimensional objects from a computer-aided design model by successively adding material layer by layer. AM has become very popular in the past decade due to its utility for fast prototyping such as 3D printing as well as manufacturing functional parts with complex geometries using processes such as laser metal deposition that would be difficult to create using traditional machining. As the process for creating an intricate part for an expensive metal such as Titanium is prohibitive with respect to cost, computational models are used to simulate the behavior of AM processes before the experimental run. However, as the simulations are computationally costly and time-consuming for predicting multiscale multi-physics phenomena in AM, physics-informed data-driven machine-learning systems for predicting the behavior of AM processes are immensely beneficial. Such models accelerate not only multiscale simulation tools but also empower real-time control systems using in-situ data. In this paper, we design and develop essential components of a scientific framework for developing a data-driven model-based real-time control system. Finite element methods are employed for solving time-dependent heat equations and developing the database. The proposed framework uses extremely randomized trees - an ensemble of bagged decision trees as the regression algorithm iteratively using temperatures of prior voxels and laser information as inputs to predict temperatures of subsequent voxels. The models achieve mean absolute percentage errors below 1% for predicting temperature profiles for AM processes. The code is made available for the research community at https://github.com/paularindam/ml-iter-additive.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122501252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Welcome to the 6th IEEE International Conference on Data Science and Advanced Analytics (DSAA’2019), the flagship annual meeting that spans the interdisciplinary fields of Data Science and Advanced Analytics. DSAA brings together researchers, industry and government practitioners, as well as developers and users of data science solutions. This creates a premier forum for an exchange of ideas on the latest theoretical developments in Data Science and on the best practice for a wide range of applications. DSAA focuses on the science of data science, as well as the implications of the science to industry, government, and society. On the science side, DSAA spans all the component fields of data science, including statistics, probabilistic and mathematical modeling, machine learning, data mining and knowledge discovery, complexity science, network science, business analytics, data management, infrastructure and storage, retrieval and search, security, privacy and ethics. On the applications side, DSAA highlights case studies and poses research obstacles motivated by applied work. DSAA showcases applications impacted by data science, presents tools and platforms that enable deployed data science solutions, and exposes researchers to challenges motivated by the application domains. As an alternative to the highly specialized disciplinary conferences, DSAA reflects the interdisciplinary nature of data science and analytics.
{"title":"Message from the Program Committee Co-Chairs","authors":"Dsaa, J. Yu","doi":"10.1109/wdfia.2008.4","DOIUrl":"https://doi.org/10.1109/wdfia.2008.4","url":null,"abstract":"Welcome to the 6th IEEE International Conference on Data Science and Advanced Analytics (DSAA’2019), the flagship annual meeting that spans the interdisciplinary fields of Data Science and Advanced Analytics. DSAA brings together researchers, industry and government practitioners, as well as developers and users of data science solutions. This creates a premier forum for an exchange of ideas on the latest theoretical developments in Data Science and on the best practice for a wide range of applications. DSAA focuses on the science of data science, as well as the implications of the science to industry, government, and society. On the science side, DSAA spans all the component fields of data science, including statistics, probabilistic and mathematical modeling, machine learning, data mining and knowledge discovery, complexity science, network science, business analytics, data management, infrastructure and storage, retrieval and search, security, privacy and ethics. On the applications side, DSAA highlights case studies and poses research obstacles motivated by applied work. DSAA showcases applications impacted by data science, presents tools and platforms that enable deployed data science solutions, and exposes researchers to challenges motivated by the application domains. As an alternative to the highly specialized disciplinary conferences, DSAA reflects the interdisciplinary nature of data science and analytics.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lei Zheng, Chun-Ta Lu, Lifang He, Sihong Xie, V. Noroozi, He Huang, Philip S. Yu
In this paper, we study the problem of modeling users' diverse interests. Previous methods usually learn a fixed user representation, which has a limited ability to represent distinct interests of a user. In order to model users' various interests, we propose a Memory Attention-aware Recommender System (MARS). MARS utilizes a memory component and a novel attentional mechanism to learn deep adaptive user representations. Trained in an end-to-end fashion, MARS adaptively summarizes users' interests. In the experiments, MARS outperforms seven state-of-the-art methods on three real-world datasets in terms of recall and mean average precision. We also demonstrate that MARS has a great interpretability to explain its recommendation results, which is important in many recommendation scenarios.
{"title":"MARS: Memory Attention-Aware Recommender System","authors":"Lei Zheng, Chun-Ta Lu, Lifang He, Sihong Xie, V. Noroozi, He Huang, Philip S. Yu","doi":"10.1109/dsaa.2019.00015","DOIUrl":"https://doi.org/10.1109/dsaa.2019.00015","url":null,"abstract":"In this paper, we study the problem of modeling users' diverse interests. Previous methods usually learn a fixed user representation, which has a limited ability to represent distinct interests of a user. In order to model users' various interests, we propose a Memory Attention-aware Recommender System (MARS). MARS utilizes a memory component and a novel attentional mechanism to learn deep adaptive user representations. Trained in an end-to-end fashion, MARS adaptively summarizes users' interests. In the experiments, MARS outperforms seven state-of-the-art methods on three real-world datasets in terms of recall and mean average precision. We also demonstrate that MARS has a great interpretability to explain its recommendation results, which is important in many recommendation scenarios.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115886238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a new low-rank tensor factorization where one mode is coded as a sparse linear combination of elements from an over-complete library. Our method, Shape Constrained Tensor Decomposition (SCTD) is based upon the CANDECOMP/PARAFAC (CP) decomposition which produces r-rank approximations of data tensors via outer products of vectors in each dimension of the data. The SCTD model can leverage prior knowledge about the shape of factors along a given mode, for example in tensor data where one mode represents time. By constraining the vector in the temporal dimension to known analytic forms which are selected from a large set of candidate functions, more readily interpretable decompositions are achieved and analytic time dependencies discovered. The SCTD method circumvents traditional flattening techniques where an N-way array is reshaped into a matrix in order to perform a singular value decomposition. A clear advantage of the SCTD algorithm is its ability to extract transient and intermittent phenomena which is often difficult for SVD-based methods. We motivate the SCTD method using several intuitively appealing results before applying it on a real-world data set to illustrate the efficiency of the algorithm in extracting interpretable spatio-temporal modes. With the rise of data-driven discovery methods, the decomposition proposed provides a viable technique for analyzing multitudes of data in a more comprehensible fashion.
{"title":"Shape Constrained Tensor Decompositions","authors":"Bethany Lusch, Eric C. Chi, J. Kutz","doi":"10.1109/DSAA.2019.00044","DOIUrl":"https://doi.org/10.1109/DSAA.2019.00044","url":null,"abstract":"We propose a new low-rank tensor factorization where one mode is coded as a sparse linear combination of elements from an over-complete library. Our method, Shape Constrained Tensor Decomposition (SCTD) is based upon the CANDECOMP/PARAFAC (CP) decomposition which produces r-rank approximations of data tensors via outer products of vectors in each dimension of the data. The SCTD model can leverage prior knowledge about the shape of factors along a given mode, for example in tensor data where one mode represents time. By constraining the vector in the temporal dimension to known analytic forms which are selected from a large set of candidate functions, more readily interpretable decompositions are achieved and analytic time dependencies discovered. The SCTD method circumvents traditional flattening techniques where an N-way array is reshaped into a matrix in order to perform a singular value decomposition. A clear advantage of the SCTD algorithm is its ability to extract transient and intermittent phenomena which is often difficult for SVD-based methods. We motivate the SCTD method using several intuitively appealing results before applying it on a real-world data set to illustrate the efficiency of the algorithm in extracting interpretable spatio-temporal modes. With the rise of data-driven discovery methods, the decomposition proposed provides a viable technique for analyzing multitudes of data in a more comprehensible fashion.","PeriodicalId":416037,"journal":{"name":"2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126468894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：