mlsanityData to 14 Oct 2026

Fair Representation Learning through Implicit Path Alignment

arXiv 2205.13316 ↗First posted 26 May 2022cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups. Specifically, we formulate this intuition as a bi-level optimization, where the representation is learned in the outer-loop, and invariant optimal group predictors are updated in the inner-loop. Moreover, the proposed bi-level objective is demonstrated to fulfill the sufficiency rule, which is desirable in various practical scenarios but was not commonly studied in the fair learning. Besides, to avoid the high computational and memory cost of differentiating in the inner-loop of bi-level objective, we propose an implicit path alignment algorithm, which only relies on the solution of inner optimization and the implicit differentiation rather than the exact optimization path. We further analyze the error gap of the implicit approach and empirically validate the proposed method in both classification and regression settings. Experimental results show the consistently better trade-off in prediction performance and fairness measurement.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

33 of 51 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2021Convex optimizationcited by 2,515
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  8. 2019Invariant Risk Minimizationcited by 1,854
  9. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  10. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  11. 2019Meta-Learning with Implicit Gradientscited by 525
  12. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
21 more
  1. 2017On Fairness and Calibrationcited by 406
  2. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  3. 2020Environment Inference for Invariant Learningcited by 306
  4. 2020The Risks of Invariant Risk Minimizationcited by 262
  5. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  6. 2016Hyperparameter optimization with approximate gradientcited by 233
  7. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  8. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  9. 2019On the Fairness of Disentangled Representationscited by 144
  10. 2019Wasserstein Fair Classificationcited by 131
  11. 2018Invariance, Causality and Robustnesscited by 123
  12. 2021Fair Mixup: Fairness via Interpolationcited by 109
  13. 2020Fair Regression with Wasserstein Barycenterscited by 100
  14. 2018Learning Controllable Fair Representationscited by 83
  15. 2019Conditional Learning of Fair Representationscited by 78
  16. 2019FAHT: An Adaptive Fairness-aware Decision Tree Classifiercited by 63
  17. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  18. 2021Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environmentscited by 30
  19. 2021On the benefits of representation regularization in invariance based domain generalizationcited by 17
  20. 2020Null-sampling for Interpretable and Fair Representationscited by 16
  21. 2020Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Boundscited by 13

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 7; 2024: 5; 2025: 6.

22 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 47
  3. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 32
  4. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  5. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  6. 2022Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothingcited by 11
  7. 2023Understanding Fairness Surrogate Functions in Algorithmic Fairnesscited by 8
  8. 2023Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptationcited by 7
  9. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  10. 2025Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metricscited by 7
  11. 2025Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functionscited by 6
  12. 2024Intersectional Unfairness Discoverycited by 5
10 more
  1. 2023Procedural Fairness Through Decoupling Objectionable Data Generating Componentscited by 3
  2. 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysiscited by 3
  3. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  4. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  5. 2024Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rulecited by 1
  6. 2025SoK: Data Minimization in Machine Learningcited by 1
  7. 2024From Discrete to Continuous: Deep Fair Clustering With Transferable Representationscited by 0
  8. 2024Back to the Drawing Board for Fair Representation Learningcited by 0
  9. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  10. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0