Deep Domain Adaptation under Deep Label Scarcity

TL;DR

This paper introduces TransDANN, a novel method combining adversarial and transductive learning to improve domain adaptation performance when source labels are scarce, supported by theoretical and experimental evidence.

Contribution

The paper proposes TransDANN, a new approach that enhances domain adaptation under label scarcity by integrating adversarial and transductive learning techniques.

Findings

TransDANN outperforms DANN in scenarios with limited source labels.

Experimental results show significant performance improvements on text and image datasets.

Theoretical analysis justifies the effectiveness of TransDANN under label scarcity.

Abstract

The goal behind Domain Adaptation (DA) is to leverage the labeled examples from a source domain so as to infer an accurate model in a target domain where labels are not available or in scarce at the best. A state-of-the-art approach for the DA is due to (Ganin et al. 2016), known as DANN, where they attempt to induce a common representation of source and target domains via adversarial training. This approach requires a large number of labeled examples from the source domain to be able to infer a good model for the target domain. However, in many situations obtaining labels in the source domain is expensive which results in deteriorated performance of DANN and limits its applicability in such scenarios. In this paper, we propose a novel approach to overcome this limitation. In our work, we first establish that DANN reduces the original DA problem into a semi-supervised learning problem over the space of common representation. Next, we propose a learning approach, namely TransDANN, that amalgamates adversarial learning and transductive learning to mitigate the detrimental impact of limited source labels and yields improved performance. Experimental results (both on text and images) show a significant boost in the performance of TransDANN over DANN under such scenarios. We also provide theoretical justification for the performance boost.