Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

TL;DR

This paper introduces an information-theoretic method for unsupervised multi-target domain adaptation, effectively learning shared and private features across multiple unlabeled target domains from a single labeled source, outperforming existing methods.

Contribution

It proposes a novel unified information-theoretic framework for disentangling shared and private features in multi-target domain adaptation, enabling simultaneous adaptation from one source to multiple unlabeled targets.

Findings

Outperforms several popular domain adaptation methods on three datasets.

Effectively disentangles shared and private domain features.

Demonstrates robustness across multiple target domains.

Abstract

Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target domains. Applying pairwise adaptation approaches to this setting may be suboptimal, as they fail to leverage shared information among multiple domains. In this work we propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain-specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data. The resulting model, accompanied by an efficient optimization algorithm, allows simultaneous adaptation from a single source to multiple target domains. We test our approach on three challenging publicly-available datasets, showing that it outperforms several popular domain adaptation methods.