We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classification
Authors:
Preprint
Abstract
The World Wide Web thrives on intelligent services that rely on accurate time series classification, which has recently witnessed significant progress driven by advances in deep learning. However, existing studies face challenges in domain incremental learning. In this paper, we propose a lightweight and robust dual-causal disentanglement framework (DualCD) to enhance the robustness of models under domain incremental scenarios, which can be seamlessly integrated into time series classification models. Specifically, DualCD first introduces a temporal feature disentanglement module to capture class-causal features and spurious features. The causal features can offer sufficient predictive power to support the classifier in domain incremental learning settings. To accurately capture these causal features, we further design a dual-causal intervention mechanism to eliminate the influence of both intra-class and inter-class confounding features. This mechanism constructs variant samples by combining the current class's causal features with intra-class spurious features and with causal features from other classes. The causal intervention loss encourages the model to accurately predict the labels of these variant samples based solely on the causal features. Extensive experiments on multiple datasets and models demonstrate that DualCD effectively improves performance in domain incremental scenarios. We summarize our rich experiments into a comprehensive benchmark to facilitate research in domain incremental time series classification.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- TimeFormer: Transformer with attention modulation empowered by temporal characteristics for time series forecastingExpert Systems with Applications, 2025
- Posterior collapse as a phase transition in variational autoencodersPhysica A: Statistical Mechanics and its Applications, 2025
- Correctformer: A transformer architecture for correcting periodic drift in time-series forecastingNeural Networks, 2025
- An attributed multiplex network enabled GNN-based stock predictor with observable and non-observable informationExpert Systems with Applications, 2025
- Domain incremental learning for object detectionPattern Recognition, 2025
- Probabilistic intervals prediction based on adaptive regression with attention residual connections and covariance constraintsEngineering Applications of Artificial Intelligence, 2025
- DuPt: Rehearsal-based continual learning with dual promptsNeural Networks, 2025
- A dynamic hypergraph attention network: Capturing market-wide spatiotemporal dependencies for stock selectionApplied Soft Computing, 2024
- Personalized Federated Domain-Incremental Learning Based on Adaptive Knowledge Matching2024
- DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning2022