Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data

2025-08-25

AI Summary

To address the degradation of generalization and robustness caused by train-test distribution shift in unsupervised time-series domain adaptation, this paper proposes an uncertainty-aware framework integrating multi-scale feature extraction with evidential deep learning. We innovatively design a multi-scale hybrid input network and introduce a Dirichlet-prior-guided cross-domain feature alignment mechanism, enabling category-consistent feature distribution modeling without target-domain labels. Simultaneously, predictive uncertainty estimation facilitates confidence calibration. Extensive experiments on multiple benchmark datasets demonstrate that our method significantly improves classification accuracy and reduces the target-domain Expected Calibration Error (ECE) by up to 32.7%, achieving state-of-the-art performance. The framework exhibits superior generalization capability and high predictive reliability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data, especially when encountering the common challenge in time series data that distribution shifts occur between training and testing datasets. In this paper, we propose incorporating multi-scale feature extraction and uncertainty estimation to improve the model's generalization and robustness across domains. Our approach begins with a multi-scale mixed input architecture that captures features at different scales, increasing training diversity and reducing feature discrepancies between the training and testing domains. Based on the mixed input architecture, we further introduce an uncertainty awareness mechanism based on evidential learning by imposing a Dirichlet prior on the labels to facilitate both target prediction and uncertainty estimation. The uncertainty awareness mechanism enhances domain adaptation by aligning features with the same labels across different domains, which leads to significant performance improvements in the target domain. Additionally, our uncertainty-aware model demonstrates a much lower Expected Calibration Error (ECE), indicating better-calibrated prediction confidence. Our experimental results show that this combined approach of mixed input architecture with the uncertainty awareness mechanism achieves state-of-the-art performance across multiple benchmark datasets, underscoring its effectiveness in unsupervised domain adaptation for time series data.

Problem

• Addressing distribution shifts in time series domain adaptation
• Improving generalization and robustness across domains
• Reducing feature discrepancies between training and testing data

Innovation

• Multi-scale feature extraction architecture
• Uncertainty estimation via evidential learning
• Domain adaptation with label alignment