mlsanityData to 14 Oct 2026

Individual Fairness Guarantees for Neural Networks

arXiv 2205.05763 ↗First posted 11 May 2022cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the ε-δ-IF formulation, which, given a NN and a similarity metric learnt from data, requires that the output difference between any pair of ε-similar individuals is bounded by a maximum decision tolerance δ ≥ 0. Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN's non-linearities globally over the input space. We encode this computation as the solution of a Mixed-Integer Linear Programming problem and demonstrate that it can be used to compute IF guarantees on four datasets widely used for fairness benchmarking. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

21 of 44 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  5. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  6. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  7. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  8. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  9. 2021Globally-Robust Neural Networkscited by 108
  10. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  11. 2020Learning Certified Individually Fair Representationscited by 69
  12. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
9 more
  1. 2019Metric Learning for Individual Fairnesscited by 52
  2. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  3. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  4. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  5. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  6. 2020Probabilistic Safety for Bayesian Neural Networkscited by 42
  7. 2021Bayesian Inference with Certifiable Adversarial Robustnesscited by 26
  8. 2017Provably Fair Representationscited by 22
  9. 2020Individual Fairness Revisited: Transferring Techniques from Adversarial Robustnesscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 6; 2025: 3; 2026: 2.

23 papers.

Sort:

  1. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  2. 2022Robust Explanation Constraints for Neural Networkscited by 24
  3. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  4. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  5. 2024FairProof : Confidential and Certifiable Fairness for Neural Networkscited by 13
  6. 2023BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programmingcited by 8
  7. 2023Adversarial Robustness Certification for Bayesian Neural Networkscited by 7
  8. 2023When to Trust AI: Advances and Challenges for Certification of Neural Networkscited by 6
  9. 2022FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networkscited by 4
  10. 2023Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spacescited by 4
  11. 2024Procedural Fairness in Machine Learningcited by 4
  12. 2024FairQuant: Certifying and Quantifying Fairness of Deep Neural Networkscited by 4
11 more
  1. 2023Individual Fairness in Bayesian Neural Networkscited by 3
  2. 2025Monitoring Robustness and Individual Fairnesscited by 3
  3. 2023Use Perturbations when Learning from Explanationscited by 2
  4. 2023Certification of Distributional Individual Fairnesscited by 2
  5. 2024Verifying the Generalization of Deep Learning to Out-of-Distribution Domainscited by 2
  6. 2024Emulating Full Participation: An Effective and Fair Client Selection Strategy for Federated Learningcited by 1
  7. 2025Correct-By-Construction: Certified Individual Fairness through Neural Network Trainingcited by 1
  8. 2026Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generationcited by 1
  9. 2026Certification-Based Differentially Private Learningcited by 1
  10. 2024Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activationscited by 0
  11. 2025SMiLE: Provably Enforcing Global Relational Properties in Neural Networkscited by 0