Papers › Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

13 Jan 2020arXiv:2001.04362archive 2025-07-28

Han Guo, Ramakanth Pasunuru, Mohit Bansal

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results. Next, we develop a DistanceNet model which uses these distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task's loss function, so as to achieve better unsupervised domain adaptation. Finally, we extend this model to a novel DistanceNet-Bandit model, which employs a multi-armed bandit controller to dynamically switch between multiple source domains and allow the model to learn an optimal trajectory and mixture of domains for transfer to the low-resource target domain. We conduct experiments on popular sentiment analysis datasets with several diverse domains and show that our DistanceNet model, as well as its dynamic bandit variant, can outperform competitive baselines in the context of unsupervised domain adaptation.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationDomain AdaptationGeneral ClassificationSentiment AnalysisText ClassificationUnsupervised Domain Adaptationtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: DistanceNet

DistanceNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections