Aggregating From Multiple Target-Shifted Sources

Abstract

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.

References in corpus (11)

• An Overview of Multi-Task Learning in Deep Neural Networks
• Marginalized Denoising Autoencoders for Domain Adaptation
• Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis
• Parameter-Efficient Transfer Learning for NLP
• A Convex Formulation for Learning Task Relationships in Multi-Task Learning
• Multiple Source Adaptation and the Renyi Divergence
• Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
• Robust Learning from Untrusted Sources
• On Target Shift in Adversarial Domain Adaptation
• Multi-source Distilling Domain Adaptation
• Multi-source Domain Adaptation for Visual Sentiment Classification