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

TL;DR

CASE-NET introduces a causal attention-based deep learning architecture for multivariate time series classification, addressing non-stationarity and noise issues to improve accuracy and robustness.

Contribution

The paper presents CASE-NET, a novel model combining causal temporal encoding and channel recalibration for better multivariate time series analysis.

Findings

Achieves state-of-the-art accuracy of 98.6% on AWR dataset.

Demonstrates superior robustness in non-stationary environments.

Outperforms existing methods across six diverse domains.

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.