CASE-Net: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification

Zhang, Fan; Cui, Yating; Wang, Hua

doi:10.24963/ijcai.2026/354

CASE-Net: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification

Fan Zhang, Yating Cui, Hua Wang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3187-3195.

https://doi.org/10.24963/ijcai.2026/354

Keywords

Machine Learning: Deep learning architectures
Machine Learning: Time series and data streams
Data Mining: Mining spatial and/or temporal data

Abstract

Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical bottlenecks: temporal non-causality in standard encoders that induces temporal confounding in non-stationary dynamics, and the absence of explicit channel saliency mechanisms that allows noise to contaminate the latent space. To address these challenges, we propose the Causal Attention and Spatio-temporal Encoder Network (CASE-Net), an architecture designed for structural manifold pre-conditioning. CASE-Net synergizes a Causal Temporal Encoder, which enforces physical arrow-of-time constraints via masked self-attention and causal convolutions, with an Adaptive Channel Recalibration module functioning as an information bottleneck to suppress detrimental noise. Comprehensive evaluations across six heterogeneous domains demonstrate that CASE-Net establishes new state-of-the-art benchmarks on four tasks, achieving a peak accuracy of 98.6% on the AWR dataset and superior robustness in non-stationary regimes.

Fan Zhang, Yating Cui, and Hua Wang. 2026. CASE-Net: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3187–3195. https://doi.org/10.24963/ijcai.2026/354

@inproceedings{ijcai2026p354,
  title     = {CASE-Net: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification},
  author    = {Zhang, Fan and Cui, Yating and Wang, Hua},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {3187--3195},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/354},
  url       = {https://doi.org/10.24963/ijcai.2026/354},
}

TY  - CPAPER
TI  - CASE-Net: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
AU  - Zhang, Fan
AU  - Cui, Yating
AU  - Wang, Hua
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 3187
EP  - 3195
DO  - 10.24963/ijcai.2026/354
UR  - https://doi.org/10.24963/ijcai.2026/354
ER  -