Accurate Online Tensor Factorization for Temporal Tensor Streams with Missing Values

Dawon Ahn, Seyun Kim, U Kang

Abstract: Given a time-evolving tensor stream with missing values, how can we accurately discover latent factors in an online manner to predict missing values? Online tensor factorization is a crucial task with many important applications including the analysis of climate, network traffic, and epidemic disease. However, existing online methods have disregarded temporal locality and thus have limited accuracy.In this paper, we propose STF (Streaming Tensor Factorization), an accurate online tensor factorization method for real-world temporal tensor streams with missing values. We exploit an attention-based temporal regularization to learn inherent temporal patterns of the streams. We also propose an efficient online learning algorithm which allows each row of the temporal factor matrix to be updated from past and future information. Extensive experiments show that the proposed method gives the state-of-the-art accuracy, and quickly processes each tensor slice.