Time and Frequency Synergy for Source-Free Time-Series Domain Adaptations

TL;DR

This paper introduces TFDA, a novel method for source-free time-series domain adaptation that leverages both time and frequency features through a dual-branch network, pseudo-labeling, contrastive learning, and curriculum strategies.

Contribution

It proposes a comprehensive framework combining time-frequency features, pseudo-labeling, contrastive learning, and curriculum learning for improved domain adaptation in time-series data.

Findings

Outperforms prior methods on benchmark datasets.

Effectively utilizes both time and frequency domain features.

Reduces domain shift uncertainties with self-distillation.

Abstract

The issue of source-free time-series domain adaptations still gains scarce research attentions. On the other hand, existing approaches rely solely on time-domain features ignoring frequency components providing complementary information. This paper proposes Time Frequency Domain Adaptation (TFDA), a method to cope with the source-free time-series domain adaptation problems. TFDA is developed with a dual branch network structure fully utilizing both time and frequency features in delivering final predictions. It induces pseudo-labels based on a neighborhood concept where predictions of a sample group are aggregated to generate reliable pseudo labels. The concept of contrastive learning is carried out in both time and frequency domains with pseudo label information and a negative pair exclusion strategy to make valid neighborhood assumptions. In addition, the time-frequency consistency technique is proposed using the self-distillation strategy while the uncertainty reduction strategy is implemented to alleviate uncertainties due to the domain shift problem. Last but not least, the curriculum learning strategy is integrated to combat noisy pseudo labels. Our experiments demonstrate the advantage of our approach over prior arts with noticeable margins in benchmark problems.