mlsanityData to 7 Oct 2026

F3: Fair and Federated Face Attribute Classification with Heterogeneous Data

arXiv 2109.02351 ↗First posted 6 Sep 2021cs.LG cs.CV cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Apart from this trend, Federated Learning (FL) is increasingly gaining traction as a scalable paradigm for distributed training. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is too restrictive in real-world settings. We propose F3, a novel FL framework for fair FAC under data heterogeneity. F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption. We demonstrate the efficacy of F3 by reporting empirically observed fairness measures and accuracy guarantees on popular face datasets. Our results suggest that F3 strikes a practical balance between accuracy and fairness for FAC.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

28 of 56 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  6. 2021Model-Contrastive Federated Learningcited by 762
  7. 2014Certifying and removing disparate impactcited by 715
  8. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  10. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  11. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  12. 2018A Reductions Approach to Fair Classificationcited by 585
16 more
  1. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  2. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  3. 2019Fair Resource Allocation in Federated Learningcited by 389
  4. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  5. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
  6. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  7. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
  8. 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 121
  9. 2020Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditingcited by 89
  10. 2019Diversity in Facescited by 77
  11. 2020Lagrangian Duality for Constrained Deep Learningcited by 72
  12. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  13. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  14. 2018FNNC: Achieving Fairness through Neural Networkscited by 43
  15. 2017Penalizing Unfairness in Binary Classificationcited by 25
  16. 2020FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regretcited by 22

Built on by

Not cited yet.