mlsanityData to 7 Oct 2026

Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary

arXiv 2101.07235 ↗First posted 18 Jan 2021stat.ML cs.AI cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

We introduce FELICIA (FEderated LearnIng with a CentralIzed Adversary) a generative mechanism enabling collaborative learning. In particular, we show how a data owner with limited and biased data could benefit from other data owners while keeping data from all the sources private. This is a common scenario in medical image analysis where privacy legislation prevents data from being shared outside local premises. FELICIA works for a large family of Generative Adversarial Networks (GAN) architectures including vanilla and conditional GANs as demonstrated in this work. We show that by using the FELICIA mechanism, a data owner with limited image samples can generate high-quality synthetic images with high utility while neither data owners has to provide access to its data. The sharing happens solely through a central discriminator that has access limited to synthetic data. Here, utility is defined as classification performance on a real test set. We demonstrate these benefits on several realistic healthcare scenarions using benchmark image datasets (MNIST, CIFAR-10) as well as on medical images for the task of skin lesion classification. With multiple experiments, we show that even in the worst cases, combining FELICIA with real data gracefully achieves performance on par with real data while most results significantly improves the utility.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 18 Jan 2021.

Builds on

19 of 34 references.

References · 19

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2014Conditional Generative Adversarial Netscited by 2,152
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2020The Future of Digital Health with Federated Learningcited by 625
  5. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  6. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  7. 2018Differentially Private Generative Adversarial Networkcited by 235
  8. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  9. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  10. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 89
  11. 2018Private Selection from Private Candidatescited by 75
  12. 2020Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directionscited by 65
7 more
  1. 2018MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasetscited by 49
  2. 2020Detect and Correct Bias in Multi-Site Neuroimaging Datasetscited by 44
  3. 2017LOGAN: Membership Inference Attacks Against Generative Modelscited by 28
  4. 2020Federated Generative Adversarial Learningcited by 19
  5. 2019Federated Generative Privacycited by 16
  6. 2020MACE: A Flexible Framework for Membership Privacy Estimation in Generative Modelscited by 5
  7. 2020Private data sharing between decentralized users through the privGAN architecturecited by 3

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 6; 2023: 3; 2024: 1.

14 papers.

Sort:

By area:

  1. 2022Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)cited by 23
  2. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  3. 2023Augmenting medical image classifiers with synthetic data from latent diffusion modelscited by 21
  4. 2023Recent Methodological Advances in Federated Learning for Healthcarecited by 11
  5. 2022A Snapshot of the Frontiers of Client Selection in Federated Learningcited by 9
  6. 2023Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Datacited by 8
  7. 2021An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprisescited by 6
  8. 2021Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentationcited by 6
  9. 2021Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligentcited by 5
  10. 2024A survey of recent methods for addressing AI fairness and bias in biomedicinecited by 5
  11. 2022Enhancing Fairness of Visual Attribute Predictorscited by 3
  12. 2022A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observationscited by 2
2 more
  1. 2022Fair Machine Learning in Healthcare: A Reviewcited by 0
  2. 2022GAN-based generative modelling for dermatological applications -- comparative studycited by 0