Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data

TL;DR

This paper introduces a novel unsupervised domain adaptation method for time series data that combines multi-scale feature extraction with uncertainty estimation to improve robustness and calibration across domains.

Contribution

It proposes a multi-scale mixed input architecture integrated with evidential uncertainty estimation, enhancing domain adaptation and prediction calibration for time series.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates lower Expected Calibration Error (ECE).

Improves robustness and generalization across domains.

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.