# Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classification

arXiv: https://arxiv.org/abs/2011.06485 · HTML: https://mlsanity.com/paper/2011.06485/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2020.

## Built on by (most cited first, 30 of 32)

- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations](https://mlsanity.com/paper/2205.03295/) (2022)
- [An Empirical Framework for Domain Generalization in Clinical Settings](https://mlsanity.com/paper/2103.11163/) (2021)
- [Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification](https://mlsanity.com/paper/2106.10826/) (2021)
- [De-biasing "bias" measurement](https://mlsanity.com/paper/2205.05770/) (2022)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [Feature robustness and sex differences in medical imaging: a case study in MRI-based Alzheimer's disease detection](https://mlsanity.com/paper/2204.01737/) (2022)
- [Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation](https://mlsanity.com/paper/2107.04212/) (2021)
- [Fairness and robustness in anti-causal prediction](https://mlsanity.com/paper/2209.09423/) (2022)
- [Designing Long-term Group Fair Policies in Dynamical Systems](https://mlsanity.com/paper/2311.12447/) (2023)
- [One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes](https://mlsanity.com/paper/2406.13544/) (2024)
- [Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation](https://mlsanity.com/paper/2201.11576/) (2022)
- [Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions](https://mlsanity.com/paper/2107.09546/) (2021)
- [Toxicity of the Commons: Curating Open-Source Pre-Training Data](https://mlsanity.com/paper/2410.22587/) (2024)
- [ABCinML: Anticipatory Bias Correction in Machine Learning Applications](https://mlsanity.com/paper/2206.06960/) (2022)
- [Learning Optimal Features via Partial Invariance](https://mlsanity.com/paper/2301.12067/) (2023)
- [Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces](https://mlsanity.com/paper/2308.08938/) (2023)
- [A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligence](https://mlsanity.com/paper/2410.17281/) (2024)
- [Identifying and Benchmarking Natural Out-of-Context Prediction Problems](https://mlsanity.com/paper/2110.13223/) (2021)
- [A Survey on Preserving Fairness Guarantees in Changing Environments](https://mlsanity.com/paper/2211.07530/) (2022)
- [Improving Identity-Robustness for Face Models](https://mlsanity.com/paper/2304.03838/) (2023)
- [AdvSumm: Adversarial Training for Bias Mitigation in Text Summarization](https://mlsanity.com/paper/2506.06273/) (2025)
- [Balancing Fairness and Robustness via Partial Invariance](https://mlsanity.com/paper/2112.09346/) (2021)
- [Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions](https://mlsanity.com/paper/2302.09190/) (2023)
- [Soft-Label Integration for Robust Toxicity Classification](https://mlsanity.com/paper/2410.14894/) (2024)
- [QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Tasks](https://mlsanity.com/paper/2601.20731/) (2026)
- [Fairness via Adversarial Attribute Neighbourhood Robust Learning](https://mlsanity.com/paper/2210.06630/) (2022)

## Abstract (arXiv)

Robustness is of central importance in machine learning and has given rise to the fields of domain generalization and invariant learning, which are concerned with improving performance on a test distribution distinct from but related to the training distribution. In light of recent work suggesting an intimate connection between fairness and robustness, we investigate whether algorithms from robust ML can be used to improve the fairness of classifiers that are trained on biased data and tested on unbiased data. We apply Invariant Risk Minimization (IRM), a domain generalization algorithm that employs a causal discovery inspired method to find robust predictors, to the task of fairly predicting the toxicity of internet comments. We show that IRM achieves better out-of-distribution accuracy and fairness than Empirical Risk Minimization (ERM) methods, and analyze both the difficulties that arise when applying IRM in practice and the conditions under which IRM will likely be effective in this scenario. We hope that this work will inspire further studies of how robust machine learning methods relate to algorithmic fairness.