CP-ORTHO: An Orthogonal Tensor Factorization Framework for Spatio-Temporal Data

被引:15
作者
Afshar, Ardavan [1 ]
Ho, Joyce C. [2 ]
Dilkina, Bistra [1 ]
Perros, Ioakeim [1 ]
Khalil, Elias B. [1 ]
Xiong, Li [2 ]
Sunderam, Vaidy [2 ]
机构
[1] Georgia Inst Technol, Atlanta, GA 30332 USA
[2] Emory Univ, Atlanta, GA 30322 USA
来源
25TH ACM SIGSPATIAL INTERNATIONAL CONFERENCE ON ADVANCES IN GEOGRAPHIC INFORMATION SYSTEMS (ACM SIGSPATIAL GIS 2017) | 2017年
基金
美国国家科学基金会;
关键词
Tensor Factorization; Unsupervised Learning; DECOMPOSITIONS;
D O I
10.1145/3139958.3140047
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Extracting patterns and deriving insights from spatio-temporal data finds many target applications in various domains, such as in urban planning and computational sustainability. Due to their inherent capability of simultaneously modeling the spatial and temporal aspects of multiple instances, tensors have been successfully used to analyze such spatio-temporal data. However, standard tensor factorization approaches often result in components that are highly overlapping, which hinders the practitioner's ability to interpret them without advanced domain knowledge. In this work, we tackle this challenge by proposing a tensor factorization framework, called CP-ORTHO, to discover distinct and easily-interpretable patterns from multi-modal, spatio-temporal data. We evaluate our approach on real data reflecting taxi drop-off activity. CP-ORTHO provides more distinct and interpretable patterns than prior art, as measured via relevant quantitative metrics, without compromising the solution's accuracy. We observe that CP-ORTHO is fast, in that it achieves this result in 5x less time than the most accurate competing approach.
引用
收藏
页数:4
相关论文
共 12 条
[1]  
Acar E., 2011, ARXIV11053422
[2]   A scalable optimization approach for fitting canonical tensor decompositions [J].
Acar, Evrim ;
Dunlavy, Daniel M. ;
Kolda, Tamara G. .
JOURNAL OF CHEMOMETRICS, 2011, 25 (02) :67-86
[3]  
Bader B. W., 2007, SIAM J SCI COMPUTING
[4]   ANALYSIS OF INDIVIDUAL DIFFERENCES IN MULTIDIMENSIONAL SCALING VIA AN N-WAY GENERALIZATION OF ECKART-YOUNG DECOMPOSITION [J].
CARROLL, JD ;
CHANG, JJ .
PSYCHOMETRIKA, 1970, 35 (03) :283-&
[5]   ON TENSORS, SPARSITY, AND NONNEGATIVE FACTORIZATIONS [J].
Chi, Eric C. ;
Kolda, Tamara G. .
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2012, 33 (04) :1272-1299
[6]  
Harshman R.A., 1970, MULTIMODAL FACTOR AN, V16
[7]   Tensor Decompositions and Applications [J].
Kolda, Tamara G. ;
Bader, Brett W. .
SIAM REVIEW, 2009, 51 (03) :455-500
[8]   Orthogonal tensor decompositions [J].
Kolda, TG .
SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2001, 23 (01) :243-255
[9]   3-WAY ARRAYS - RANK AND UNIQUENESS OF TRILINEAR DECOMPOSITIONS, WITH APPLICATION TO ARITHMETIC COMPLEXITY AND STATISTICS [J].
KRUSKAL, JB .
LINEAR ALGEBRA AND ITS APPLICATIONS, 1977, 18 (02) :95-138
[10]   Projected gradient methods for nonnegative matrix factorization [J].
Lin, Chih-Jen .
NEURAL COMPUTATION, 2007, 19 (10) :2756-2779