首页

首页 > 学术科研 > 正文

首页

学术科研
战略所人物
活动会议
合作交流
战略所动态
通知公告
视频

学术科研

Distribution Matching for Self-Supervised Transfer Learning

题目Distribution Matching for Self-Supervised Transfer Learning
作者Jiao,Yuling Ma,Wensen Sun,Defeng Wang,Hansheng Wang,Yang
作者单位School of Artificial Intelligence, School of Mathematics and Statistics, Wuhan University, Wuhan, China School of Mathematics and Statistics, Wuhan University, Wuhan, China Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong Guanghua School of Management, Peking University, Beijing, China Department of Mathematics, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
关键词：Self-supervised learning Adversarial machine learning - Contrastive Learning - Federated learning - Supervised learning - Transfer learning
时间：2025年2月20日
出版者：arXiv
摘要In this paper, we propose a novel self-supervised transfer learning method called Distribution Matching (DM), which drives the representation distribution toward a predefined reference distribution while preserving augmentation invariance. The design of DM results in a learned representation space that is intuitively structured and offers easily interpretable hyperparameters. Experimental results across multiple real-world datasets and evaluation metrics demonstrate that DM performs competitively on target classification tasks compared to existing self-supervised transfer learning methods. Additionally, we provide robust theoretical guarantees for DM, including a population theorem and an end-to-end sample theorem. The population theorem bridges the gap between the self-supervised learning task and target classification accuracy, while the sample theorem shows that, even with a limited number of samples from the target domain, DM can deliver exceptional classification performance, provided the unlabeled sample size is sufficiently large. Copyright ?? 2025, The Authors. All rights reserved.
URLhttp://hdl.handle.net/20.500.11897/741144
ISSN10.48550/arXiv.2502.14424
收录情况EI
作者单位 School of Artificial Intelligence, School of Mathematics and Statistics, Wuhan University, Wuhan, China School of Mathematics and Statistics, Wuhan University, Wuhan, China Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong Guanghua School of Management, Peking University, Beijing, China Department of Mathematics, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong 时间 2025年2月20日
出版者 arXiv URL http://hdl.handle.net/20.500.11897/741144
ISSN 10.48550/arXiv.2502.14424 DOI
收录情况 EI 分类
TOP