This paper advances the theory and practice of Domain Generalization (DG) in machine learning. We consider the typical DG setting where the hypothesis is composed of a representation mapping followed by a labeling function. Within this setting, the majority of popular DG methods aim to jointly learn the representation and the labeling functions by minimizing a well-known upper bound for the classification risk in the unseen domain. In practice, however, methods based on this theoretical upper bound ignore a term that cannot be directly optimized due to its dual dependence on both the representation mapping and the unknown optimal labeling function in the unseen domain. To bridge this gap between theory and practice, we introduce a new upper bound that is free of terms having such dual dependence, resulting in a fully optimizable risk upper bound for the unseen domain. Our derivation leverages classical and recent transport inequalities that link optimal transport metrics with information-theoretic measures. Compared to previous bounds, our bound introduces two new terms: (i) the Wasserstein-2 barycenter term that aligns distributions between domains, and (ii) the reconstruction loss term that assesses the quality of representation in reconstructing the original data. Based on this new upper bound, we propose a novel DG algorithm named Wasserstein Barycenter Auto-Encoder (WBAE) that simultaneously minimizes the classification loss, the barycenter loss, and the reconstruction loss. Numerical results demonstrate that the proposed method outperforms current state-of-the-art DG algorithms on several datasets.
Barycentric alignment for instance-level comparison of neural representations
Department of XXX, University of YYY, Location, Country（YYY大学XXX系）；School of ZZZ, Institute of WWW, Location, Country（WWW研究所ZZZ学院）；Department of Electrical and Computer Engineering, UCSD（UCSD电子与计算机工程系）；Cognitive Science Department, UCSD（UCSD认知科学系）；Department of Computer Science（计算机科学系）
M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognition
School of Biomedical Engineering, Medical School, Shenzhen University（生物医学工程学院，医学学院，深圳大学）；School of Public Health, Shenzhen University Medical School（公共卫生学院，深圳大学医学学院）；Department of Radiology, Nanshan Hospital of Shenzhen University（放射科，深圳大学南山医院）；School of Mathematical Sciences, Shenzhen University（数学科学学院，深圳大学）；Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（申明武智能工程学院，华南理工大学）；Institute for Super Robotics, Guangzhou, Guangdong, China（超机器人研究所，广州，广东，中国）
Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Shanghai Key Laboratory of Digital Media Processing and Transmission（上海市数字媒体处理与传输重点实验室）
A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport
New York University, NYUAD, Division of Science, Computer Science Department（纽约大学，NYUAD，科学学院，计算机科学系）；University of Quebec in Montreal, Computer Science Department, Montreal（魁北克大学蒙特利尔分校，计算机科学系，蒙特利尔）；University of Edinburgh, School of Informatics, Edinburgh（爱丁堡大学，信息学院，爱丁堡）
Scalable unsupervised alignment of general metric and non-metric structures
Technion – Israel Institute of Technology（以色列理工学院）；Institute of Science and Technology, Austria（奥地利科学技术研究所）；Sapienza University of Rome（罗马大学）；University of Trieste（的里雅斯特大学）
