# Modular Domain Adaptation

arXiv: https://arxiv.org/abs/2204.14213 · HTML: https://mlsanity.com/paper/2204.14213/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 26 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Learning to Generate Reviews and Discovering Sentiment](https://mlsanity.com/paper/1704.01444/) (2017)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)
- [Regularized Learning for Domain Adaptation under Label Shifts](https://mlsanity.com/paper/1903.09734/) (2019)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [Causal Effects of Linguistic Properties](https://mlsanity.com/paper/2010.12919/) (2020)
- [Pre-train or Annotate? Domain Adaptation with a Constrained Budget](https://mlsanity.com/paper/2109.04711/) (2021)
- [Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora](https://mlsanity.com/paper/1606.02820/) (2016)
- [How we do things with words: Analyzing text as social and cultural data](https://mlsanity.com/paper/1907.01468/) (2019)
- [Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes](https://mlsanity.com/paper/2006.14209/) (2020)

## Built on by (most cited first, 1 of 1)

- [On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.03154/) (2022)

## Abstract (arXiv)

Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment. However, without access to source data it is difficult to account for domain shift, which represents a threat to validity. Here, we treat domain adaptation as a modular process that involves separate model producers and model consumers, and show how they can independently cooperate to facilitate more accurate measurements of text. We introduce two lightweight techniques for this scenario, and demonstrate that they reliably increase out-of-domain accuracy on four multi-domain text classification datasets when used with linear and contextual embedding models. We conclude with recommendations for model producers and consumers, and release models and replication code to accompany this paper.