Robust Multi-Source Domain Adaptation under Label Shift

2025-03-04 · Congbin Xu, Chengde Qian, Zhaojun Wang, Changliang Zou

As the volume of data continues to expand, it becomes increasingly common for data to be aggregated from multiple sources. Leveraging multiple sources for model training typically achieves better predictive performance on test datasets. Unsupervised multi-source domain adaptation aims to predict labels of unlabeled samples in the target domain by using labeled samples from source domains. This work focuses on robust multi-source domain adaptation for multi-category classification problems against the heterogeneity of label shift and data contamination. We investigate a domain-weighted empirical risk minimization framework for robust estimation of the target domain's class proportion. Inspired by outlier detection techniques, we propose a refinement procedure within this framework. With the estimated class proportion, robust classifiers for the target domain can be constructed. Theoretically, we study the finite-sample error bounds of the domain-weighted empirical risk minimization and highlight the improvement of the refinement step. Numerical simulations and real-data applications demonstrate the superiority of the proposed method.

📄 PDF Abstract BibTeX arXiv:2503.02506

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Outlier Detection

Ensemble Multi-Source Domain Adaptation with Pseudolabels

2020-09-29 · Seongmin Lee, Hyunsik Jeon, U Kang

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset…

Domain Adaptation Ensemble Learning

Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation

2025-02-05 · Zhen Zhang, Bingsheng He

Unsupervised graph domain adaptation (UGDA) focuses on transferring knowledge from labeled source graph to unlabeled target graph under domain discrepancies. Most existing UGDA methods are designed to adapt information f…

Domain Adaptation GRAPH DOMAIN ADAPTATION

FREEDOM: Target Label & Source Data & Domain Information-Free Multi-Source Domain Adaptation for Unsupervised Personalization

2023-07-04 · Eunju Yang, Gyusang Cho, Chan-Hyun Youn

From a service perspective, Multi-Source Domain Adaptation (MSDA) is a promising scenario to adapt a deployed model to a client's dataset. It can provide adaptation without a target label and support the case where a sou…

Domain Adaptation Philosophy

Universal Multi-Source Domain Adaptation

2020-11-05 · Yueming Yin, Zhen Yang, Haifeng Hu, Xiaofu Wu

Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one sourc…

Domain Adaptation Universal Domain Adaptation Unsupervised Domain Adaptation

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

2021-03-08 · CVPR 2021 1 · Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framew…

Domain Adaptation Multi-Source Unsupervised Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation