Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we analyzed the problem for aggregating source domains with different label distributions, where most recent source selection approaches fail. Our proposed algorithm differs from previous approaches in two key ways: the model aggregates multiple sources mainly through the similarity of semantic conditional distribution rather than marginal distribution; the model proposes a \emph{unified} framework to select relevant sources for three popular scenarios, i.e., domain adaptation with limited label on target domain, unsupervised domain adaptation and label partial unsupervised domain adaption. We evaluate the proposed method through extensive experiments. The empirical results significantly outperform the baselines.
Representational Transfer Learning for Matrix Completion
Institute for Financial Studies, Shandong University(山东大学金融研究院);School of Management, Fudan University(复旦大学管理学院);School of Physical & Mathematical Sciences, Nanyang Technological University(南洋理工大学数理学院);Department of Statistics and Data Science, National University of Singapore(新加坡国立大学统计与数据科学系)
TILT: Target-induced loss tilting under covariate shift
Lab for Information and Decision Systems(信息与决策系统实验室);Statistics and Data Science Center(统计与数据科学中心);EECS, Massachusetts Institute of Technology(麻省理工学院电子工程与计算机科学系);Mathematics and EECS, Massachusetts Institute of Technology(数学与电子工程与计算机科学系, 麻省理工学院)
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)
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications
Idiap Research Institute(伊迪亚普研究所);Ecole Polytechnique Federale de Lausanne (EPFL)(洛桑联邦理工学院);Brno University of Technology(布尔诺理工大学);German Aerospace Center (DLR)(德国航空航天中心);Beijing Institute of Technology(北京理工大学)
Overcoming label shift with target-aware federated learning
RISE Research Institutes of Sweden(瑞典RISE研究机构);KTH Royal Institute of Technology(皇家理工学院);Chalmers University of Technology(查尔姆斯理工大学);University of Gothenburg(哥德堡大学)