Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space

Abstract

This paper seeks to solve Multi-Source Domain Adaptation (MSDA), which aims to mitigate data distribution shifts when transferring knowledge from multiple labeled source domains to an unlabeled target domain. We propose a novel MSDA framework based on dictionary learning and optimal transport. We interpret each domain in MSDA as an empirical distribution. As such, we express each domain as a Wasserstein barycenter of dictionary atoms, which are empirical distributions. We propose a novel algorithm, DaDiL, for learning via mini-batches: (i) atom distributions; (ii) a matrix of barycentric coordinates. Based on our dictionary, we propose two novel methods for MSDA: DaDil-R, based on the reconstruction of labeled samples in the target domain, and DaDiL-E, based on the ensembling of classifiers learned on atom distributions. We evaluate our methods in 3 benchmarks: Caltech-Office, Office 31, and CRWU, where we improved previous state-of-the-art by 3.15%, 2.29%, and 7.71% in classification performance. Finally, we show that interpolations in the Wasserstein hull of learned atoms provide data that can generalize to the target domain.

13 pages,8 figures,Published as a conference paper at the 26th European Conference on Artificial Intelligence; v2: corrected typos

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Geometric Dataset Distances via Optimal Transport
• Minibatch optimal transport distances; analysis and applications
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Recent Advances in Optimal Transport for Machine Learning