Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning
Not on the map. Why?
Abstract (arXiv)
Multi-mode tensor time series (TTS) can be found in many domains, such as search engines and environmental monitoring systems. Learning representations of a TTS benefits various applications, but it is also challenging since the complexities inherent in the tensor hinder the realization of rich representations. In this paper, we propose a novel representation learning method designed specifically for TTS, namely MoST. Specifically, MoST uses a tensor slicing approach to reduce the complexity of the TTS structure and learns representations that can be disentangled into individual non-temporal modes. Each representation captures mode-specific features, which are the relationship between variables within the same mode, and mode-invariant features, which are in common in representations of different modes. We employ a contrastive learning framework to learn parameters; the loss function comprises two parts intended to learn representation in a mode-specific way and mode-invariant way, effectively exploiting disentangled representations as augmentations. Extensive experiments on real-world datasets show that MoST consistently outperforms the state-of-the-art methods in terms of classification and forecasting accuracy. Code is available at https://github.com/KoheiObata/MoST.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 27 Feb 2026.
Builds on
26 of 37 references.
References · 26
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
- 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
- 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
- 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
- 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
- 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 171
- 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 143
- 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
- 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
- 2020Time Series Change Point Detection with Self-Supervised Contrastive Predictive Codingcited by 58
14 more
- 2020PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecastingcited by 52
- 2023Soft Contrastive Learning for Time Seriescited by 49
- 2021A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectivescited by 41
- 2018Generalized Canonical Polyadic Tensor Decompositioncited by 34
- 2021Network of Tensor Time Seriescited by 32
- 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
- 2021SSMF: Shifting Seasonal Matrix Factorizationcited by 11
- 2021Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representationcited by 11
- 2024Dynamic Multi-Network Mining of Tensor Time Seriescited by 8
- 2021ATD: Augmenting CP Tensor Decomposition by Self Supervisioncited by 7
- 2021Robust Factorization of Real-world Tensor Streams with Patterns, Missing Values, and Outlierscited by 6
- 2023Learning Gaussian Mixture Representations for Tensor Time Series Forecastingcited by 6
- 2024Mining of Switching Sparse Networks for Missing Value Imputation in Multivariate Time Seriescited by 5
- 2022Mining Reaction and Diffusion Dynamics in Social Activitiescited by 3
Built on by
Not cited yet.