[2602.23663] Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning

Computer Science > Machine Learning arXiv:2602.23663 (cs) [Submitted on 27 Feb 2026] Title:Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning Authors:Kohei Obata, Taichi Murayama, Zheng Chen, Yasuko Matsubara, Yasushi Sakurai View a PDF of the paper titled Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning, by Kohei Obata and 4 other authors View PDF HTML (experimental) Abstract: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 rep...