Unsupervised Domain Adaptation using Graph Transduction Games

TL;DR

This paper introduces a game-theoretic approach to unsupervised domain adaptation, using graph transduction games to assign labels to unlabeled target data with guaranteed convergence and uncertainty quantification.

Contribution

It presents a novel, principled game-theoretic framework for UDA with an automatic iterative algorithm that guarantees termination at a Nash equilibrium.

Findings

Effective on object recognition benchmarks

Outperforms some existing UDA methods

Provides soft labels indicating uncertainty

Abstract

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in a game-theoretic setting as a non-cooperative game and introduce a fully automatized iterative algorithm for UDA based on graph transduction games (GTG). The main advantages of this approach are its principled foundation, guaranteed termination of the iterative algorithms to a Nash equilibrium (which corresponds to a consistent labeling condition) and soft labels quantifying the uncertainty of the label assignment process. We also investigate the beneficial effect of using pseudo-labels from linear classifiers to initialize the iterative process. The performance of the resulting methods is assessed on publicly available object recognition benchmark datasets involving both shallow and deep features. Results of experiments demonstrate the suitability of the proposed game-theoretic approach for solving UDA tasks.