# What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training

arXiv: https://arxiv.org/abs/1805.06088 · HTML: https://mlsanity.com/paper/1805.06088/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 17 of 17)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Diverse Adversaries for Mitigating Bias in Training](https://mlsanity.com/paper/2101.10001/) (2021)
- [Balancing out Bias: Achieving Fairness Through Balanced Training](https://mlsanity.com/paper/2109.08253/) (2021)
- [UDALM: Unsupervised Domain Adaptation through Language Modeling](https://mlsanity.com/paper/2104.07078/) (2021)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training](https://mlsanity.com/paper/2109.02284/) (2021)
- [Language Variety Identification with True Labels](https://mlsanity.com/paper/2303.01490/) (2023)
- [Towards Equal Opportunity Fairness through Adversarial Learning](https://mlsanity.com/paper/2203.06317/) (2022)
- [Explainable Misinformation Detection Across Multiple Social Media Platforms](https://mlsanity.com/paper/2203.11724/) (2022)
- [Cross-Lingual Transfer Learning for Statistical Type Inference](https://mlsanity.com/paper/2107.00157/) (2021)
- [ASAT: Adaptively Scaled Adversarial Training in Time Series](https://mlsanity.com/paper/2108.08976/) (2021)
- [Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.03461/) (2024)
- [Multi-Domain Explainability of Preferences](https://mlsanity.com/paper/2505.20088/) (2025)
- [JurisCTC: Enhancing Legal Judgment Prediction via Cross-Domain Transfer and Contrastive Learning](https://mlsanity.com/paper/2504.17264/) (2025)
- [Utilizing Out-Domain Datasets to Enhance Multi-Task Citation Analysis](https://mlsanity.com/paper/2202.10884/) (2022)
- [Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification](https://mlsanity.com/paper/2409.13787/) (2024)

## Abstract (arXiv)

Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (in domain) and dissimilar (out of domain) instances to those seen in training. This requires learning an underlying task, while not learning irrelevant signals and biases specific to individual domains. We propose a novel method to optimise both in- and out-of-domain accuracy based on joint learning of a structured neural model with domain-specific and domain-general components, coupled with adversarial training for domain. Evaluating on multi-domain language identification and multi-domain sentiment analysis, we show substantial improvements over standard domain adaptation techniques, and domain-adversarial training.