Ensemble Multi-Source Domain Adaptation with Pseudolabels

TL;DR

This paper introduces EnMDAP, a novel ensemble-based method for multi-source domain adaptation that uses pseudolabels and label-wise moment matching to better align conditional distributions, achieving state-of-the-art results.

Contribution

EnMDAP is the first to combine ensemble learning with pseudolabels and label-wise moment matching for improved multi-source domain adaptation.

Findings

EnMDAP outperforms existing methods on image and text domain tasks.

Using multiple feature extractors improves adaptation accuracy.

Label-wise moment matching effectively aligns conditional distributions.

Abstract

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels. MSDA is a crucial problem applicable to many practical cases where labels for the target data are unavailable due to privacy issues. Existing MSDA frameworks are limited since they align data without considering conditional distributions p(x|y) of each domain. They also miss a lot of target label information by not considering the target label at all and relying on only one feature extractor. In this paper, we propose Ensemble Multi-source Domain Adaptation with Pseudolabels (EnMDAP), a novel method for multi-source domain adaptation. EnMDAP exploits label-wise moment matching to align conditional distributions p(x|y), using pseudolabels for the unavailable target labels, and introduces ensemble learning theme by using multiple feature extractors for accurate domain adaptation. Extensive experiments show that EnMDAP provides the state-of-the-art performance for multi-source domain adaptation tasks in both of image domains and text domains.