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

arXiv: https://arxiv.org/abs/2001.04362 · HTML: https://mlsanity.com/paper/2001.04362/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

## Built on by (most cited first, 30 of 30)

- [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://mlsanity.com/paper/2102.06828/) (2021)
- [UDALM: Unsupervised Domain Adaptation through Language Modeling](https://mlsanity.com/paper/2104.07078/) (2021)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [Can Explanations Be Useful for Calibrating Black Box Models?](https://mlsanity.com/paper/2110.07586/) (2021)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2202.00796/) (2022)
- [Secure Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2106.12124/) (2021)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering](https://mlsanity.com/paper/2306.06779/) (2023)
- [Hidden Biases in Unreliable News Detection Datasets](https://mlsanity.com/paper/2104.10130/) (2021)
- [How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?](https://mlsanity.com/paper/2401.17514/) (2024)
- [Domain adaptation in small-scale and heterogeneous biological datasets](https://mlsanity.com/paper/2405.19221/) (2024)
- [A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning](https://mlsanity.com/paper/2502.04242/) (2025)
- [Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation](https://mlsanity.com/paper/2107.01598/) (2021)
- [Jacobian Norm for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2204.03467/) (2022)
- [Domain Confused Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.04564/) (2022)
- [Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning](https://mlsanity.com/paper/2112.02922/) (2021)
- [Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifiers](https://mlsanity.com/paper/2201.11870/) (2022)
- [UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation](https://mlsanity.com/paper/2405.01022/) (2024)
- [Distributionally Robust Domain Adaptation](https://mlsanity.com/paper/2210.16894/) (2022)
- [A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets](https://mlsanity.com/paper/2304.00483/) (2023)
- [Robust Stance Detection: Understanding Public Perceptions in Social Media](https://mlsanity.com/paper/2309.15176/) (2023)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation](https://mlsanity.com/paper/2311.10806/) (2023)
- [Towards Domain Adaptive Neural Contextual Bandits](https://mlsanity.com/paper/2406.09564/) (2024)
- [Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework](https://mlsanity.com/paper/2601.10779/) (2026)
- [Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification](https://mlsanity.com/paper/2303.09115/) (2023)
- [Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptation](https://mlsanity.com/paper/2307.14068/) (2023)
- [Efficient Multi-domain Text Recognition Deep Neural Network Parameterization with Residual Adapters](https://mlsanity.com/paper/2401.00971/) (2024)
- [GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation](https://mlsanity.com/paper/2510.22214/) (2025)

## Abstract (arXiv)

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.