Domain Generalization via Selective Consistency Regularization for Time Series Classification
원문 초록
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain generalization seek to extract domain-invariant features by minimizing the discrepancy between feature distributions across all domains, disregarding inter-domain relationships. In this paper, we instead propose a novel representation learning methodology that selectively enforces prediction consistency between source domains estimated to be closely-related. Specifically, we hypothesize that domains share different class-informative representations, so instead of aligning all domains which can cause negative transfer, we only regularize the discrepancy between closely-related domains. We apply our method to time-series classification tasks and conduct comprehensive experiments on three public real-world datasets. Our method significantly improves over the baseline and achieves better or competitive performance in comparison with state-of-the-art methods in terms of both accuracy and model calibration.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Joint-Entropy Approach To Time-series Classification
Semi-supervised Time Series Classification by Temporal Relation Prediction
Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention
Support Vector Machines with Time Series Distance Kernels for Action Classification
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
A Better Alternative to Piecewise Linear Time Series Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.