Skip to yearly menu bar Skip to main content


Aggregating From Multiple Target-Shifted Sources

Changjian Shui · Zijian Li · Jiaqi Li · Christian Gagne · Charles X. Ling · Boyu Wang


Keywords: [ Algorithms ] [ Multitask, Transfer, and Meta Learning ] [ Convex Optimization; Theory ] [ Spaces of Functions and Kernels ]


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 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.

Chat is not available.