Multi-Source Domain Adaptation

Follow this topic Ask about this topic

Multi-source domain adaptation studies how to use data or models from several source domains when the target domain has a different distribution and few or no labels. Common approaches select or weight relevant sources, align features or class-conditional distributions, combine specialist models, or use shared representations and generative transformations. These methods support tasks such as medical-image segmentation, autonomous-driving perception, forecasting, and cross-site brain analysis, where data from multiple institutions or settings can improve target performance. A central challenge is avoiding negative transfer: heterogeneous sources may conflict, and stronger domain invariance or broader training does not always preserve task-relevant information or guarantee robustness on unseen targets.

Latest papers

31 papers3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decoding
Jul 28, 2025Jinzhou Wu, Baoping Tang, Qikang Li +3Cross-Subject EEG Decoding Multi-Source Domain Adaptation
State Key Laboratory of Mechanical Transmission, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China · Department of Computer Science, Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands · Machine Learning Group, UiT–The Arctic University of Norway, 9019 Tromsø, Norway

Jul 28, 2025J/K move · Enter open · S save

Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decoding

Jinzhou Wu, Baoping Tang, Qikang Li, Yi Wang+2

State Key Laboratory of Mechanical Transmission, College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044, China · Department of Computer Science, Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands · Machine Learning Group, UiT–The Arctic University of Norway, 9019 Tromsø, Norway

Cross-Subject EEG Decoding Multi-Source Domain Adaptation MI Classification

Open paper AskPDF arXiv

Cross-subject motor-imagery electroencephalography (MI-EEG) decoding remains challenging because substantial inter-subject variability can cause both negative transfer from poorly matched source subjects and persistent distribution discrepancies between source and target domains. Existing multi-source domain adaptation methods often incorporate all available source domains or estimate source relevance using signal-level or task-specific representations, while distribution alignment is frequently performed only at the feature level. These limitations may introduce irrelevant source knowledge and fail to preserve class-discriminative structures across subjects. In this study, we propose a brain foundation model-guided multi-source domain adaptation framework (BFM-MSDA) for cross-subject MI-EEG decoding. The method first utilizes representations learned by a pretrained brain foundation model to estimate source--target compatibility and retrieve target-relevant sources. Subsequently, a relevance-weighted dual alignment strategy is applied to the selected sources and the unlabeled target domain. Specifically, Cauchy--Schwarz (CS) divergence is used to reduce discrepancies in marginal feature distributions, while conditional Cauchy--Schwarz (CCS) divergence further aligns class-dependent decision distributions. Source relevance is incorporated into both alignment terms so that more transferable source subjects contribute more strongly to adaptation. Experiments on two public MI-EEG benchmarks achieve average accuracies of 86.16% and 78.41%, outperforming representative cross-subject decoding and domain adaptation methods. Additional experiments with a large source pool further demonstrate that target-aware source retrieval improves scalability while mitigating negative transfer. These results highlight the importance of informed source selection under cross-subject distribution shift.