mlsanityData to 7 Oct 2026

Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation

arXiv 2410.01423 ↗First posted 2 Oct 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first train a teacher model to create fair representation and then distil the knowledge to a student model (using a smaller architecture). The process of distilling the student model is data-free, i.e. the student model does not have access to the training dataset while distilling. After the distillation, we use the distilled model to generate fair synthetic samples. Our extensive experiments show that our synthetic samples outperform state-of-the-art models in all three criteria (fairness, utility and synthetic quality) with a performance increase of 5% for fairness, 8% for utility and 12% in synthetic quality for both tabular and image datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 2 Oct 2024.

Builds on

24 of 38 references.

References · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  7. 2020Fairness in Machine Learning: A Surveycited by 369
  8. 2022Knowledge Distillation from A Stronger Teachercited by 204
  9. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  10. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  11. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  12. 2019Fair Generative Modeling via Weak Supervisioncited by 114
12 more
  1. 2022Curriculum Temperature for Knowledge Distillationcited by 110
  2. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  3. 2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
  4. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  5. 2021TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networkscited by 34
  6. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29
  7. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  8. 2023The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillationcited by 16
  9. 2023RELIANT: Fair Knowledge Distillation for Graph Neural Networkscited by 10
  10. 2024Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networkscited by 4
  11. 2024FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainabilitycited by 2
  12. 2024Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representationcited by 1

Built on by

Not cited yet.