Conference Proceedings

Accelerating online CP decompositions for higher order tensors

S Zhou, NX Vinh, J Bailey, Y Jia, I Davidson

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining | Association for Computing Machinery (ACM) | Published : 2016

DOI: 10.1145/2939672.2939763

Abstract

© 2016 ACM. Tensors are a natural representation for multidimensional data. In recent years, CANDECOMP/PARAFAC (CP) decomposition, one of the most popular tools for analyzing multi-way data, has been extensively studied and widely applied. However, today's datasets are often dynamically changing over time. Tracking the CP decomposition for such dynamic tensors is a crucial but challenging task, due to the large scale of the tensor and the velocity of new data arriving. Traditional techniques, such as Alternating Least Squares (ALS), cannot be directly applied to this problem because of their poor scalability in terms of time and memory. Additionally, existing online approaches have only part..

View full abstract

Related Projects (1)

Project icon

Multi Source Inference From Heterogeneous Dynamic Networks

Sophisticated big data applications in engineering, the social sciences and biology are now generating flows of data across multiple sources..

Grants

Awarded by Australian Research Council

Funding Acknowledgements

This work is supported by the Australian Research Council via grant number DP140101969.

Citation metrics

10Web of Science
32Scopus

Keywords

Tensor Decomposition
Computer Science, Information Systems
Science & Technology
Cp Decomposition
Computer Science
Online Learning
Technology
Computer Science, Theory & Methods
Computer Science, Artificial Intelligence