# FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

arXiv: https://arxiv.org/abs/2002.10234 · HTML: https://mlsanity.com/paper/2002.10234/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2020.

## Built on by (most cited first, 30 of 52)

- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [On Tilted Losses in Machine Learning: Theory and Applications](https://mlsanity.com/paper/2109.06141/) (2021)
- [Improving Fairness via Federated Learning](https://mlsanity.com/paper/2110.15545/) (2021)
- [Fairness Reprogramming](https://mlsanity.com/paper/2209.10222/) (2022)
- [Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization](https://mlsanity.com/paper/2306.09264/) (2023)
- [A Stochastic Optimization Framework for Fair Risk Minimization](https://mlsanity.com/paper/2102.12586/) (2021)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [Optimising Equal Opportunity Fairness in Model Training](https://mlsanity.com/paper/2205.02393/) (2022)
- [Poisoning Attacks on Fair Machine Learning](https://mlsanity.com/paper/2110.08932/) (2021)
- [FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification](https://mlsanity.com/paper/2407.08813/) (2024)
- [Fairness-Aware PAC Learning from Corrupted Data](https://mlsanity.com/paper/2102.06004/) (2021)
- [Information-theoretic regularization for Multi-source Domain Adaptation](https://mlsanity.com/paper/2104.01568/) (2021)
- [Improving Fair Training under Correlation Shifts](https://mlsanity.com/paper/2302.02323/) (2023)
- [Equal Improvability: A New Fairness Notion Considering the Long-term Impact](https://mlsanity.com/paper/2210.06732/) (2022)
- [FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scaling](https://mlsanity.com/paper/2310.02492/) (2023)
- [Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2405.08681/) (2024)
- [FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling](https://mlsanity.com/paper/2311.02189/) (2023)
- [On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms](https://mlsanity.com/paper/2402.18129/) (2024)
- [Fair Training of Decision Tree Classifiers](https://mlsanity.com/paper/2101.00909/) (2021)
- [Breaking Fair Binary Classification with Optimal Flipping Attacks](https://mlsanity.com/paper/2204.05472/) (2022)
- [Prototype Based Classification from Hierarchy to Fairness](https://mlsanity.com/paper/2205.13997/) (2022)
- [Fairness-aware Regression Robust to Adversarial Attacks](https://mlsanity.com/paper/2211.04449/) (2022)
- [LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views](https://mlsanity.com/paper/2402.04644/) (2024)
- [Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency](https://mlsanity.com/paper/2403.00625/) (2024)

## Abstract (arXiv)

Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, resulting in severe performance degradation. To address this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.