mlsanityData to 14 Oct 2026

MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets

arXiv 1811.03850 ↗First posted 9 Nov 2018cs.LG stat.MLcited by 49

Not on the map. Why?

Abstract (arXiv)

A recent technical breakthrough in the domain of machine learning is the discovery and the multiple applications of Generative Adversarial Networks (GANs). Those generative models are computationally demanding, as a GAN is composed of two deep neural networks, and because it trains on large datasets. A GAN is generally trained on a single server. In this paper, we address the problem of distributing GANs so that they are able to train over datasets that are spread on multiple workers. MD-GAN is exposed as the first solution for this problem: we propose a novel learning procedure for GANs so that they fit this distributed setup. We then compare the performance of MD-GAN to an adapted version of Federated Learning to GANs, using the MNIST and CIFAR10 datasets. MD-GAN exhibits a reduction by a factor of two of the learning complexity on each worker node, while providing better performances than federated learning on both datasets. We finally discuss the practical implications of distributing GANs.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 11; 2023: 6; 2024: 9; 2025: 5; 2026: 1.

49 papers.

Sort:

By area:

  1. 2021Diffusion-Based Representation Learningcited by 57
  2. 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
  3. 2021Generative adversarial networks in time series: A survey and taxonomycited by 21
  4. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  5. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  6. 2021Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversarycited by 14
  7. 2022FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networkscited by 12
  8. 2022Training Mixed-Domain Translation Models via Federated Learningcited by 12
  9. 2023Consistent Distributed Ranking of Generative Models via Kernel Distancescited by 10
  10. 2021Fed-TGAN: Federated Learning Framework for Synthesizing Tabular Datacited by 9
  11. 2021Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networkscited by 8
  12. 2021Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approachcited by 8
37 more
  1. 2022FedSyn: Synthetic Data Generation using Federated Learningcited by 7
  2. 2025Federated Learning for Diffusion Modelscited by 7
  3. 2021Game of GANs: Game-Theoretical Models for Generative Adversarial Networkscited by 6
  4. 2023FLAIM: AIM-based Synthetic Data Generation in the Federated Settingcited by 6
  5. 2022Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimationcited by 5
  6. 2022Federated Split GANscited by 4
  7. 2024CollaFuse: Collaborative Diffusion Modelscited by 4
  8. 2021Bi-Discriminator Class-Conditional Tabular GANcited by 3
  9. 2022EFFGAN: Ensembles of fine-tuned federated GANscited by 3
  10. 2025PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Modelscited by 3
  11. 2021Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescencecited by 2
  12. 2022MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-IID distributioncited by 2
  13. 2022Modeling Global Distribution for Federated Learning with Label Distribution Skewcited by 2
  14. 2023MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characterscited by 2
  15. 2021Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasetscited by 1
  16. 2021Federated Traffic Synthesizing and Classification Using Generative Adversarial Networkscited by 1
  17. 2021Towards convergence to Nash equilibria in two-team zero-sum gamescited by 1
  18. 2022Attacks and Defenses for Free-Riders in Multi-Discriminator GANcited by 1
  19. 2022Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learningcited by 1
  20. 2023ApproxED: Approximate exploitability descent via learned best responsescited by 1
  21. 2024Private Knowledge Sharing in Distributed Learning: A Surveycited by 1
  22. 2025Rebalancing the Scales: A Systematic Mapping Study of Generative Adversarial Networks (GANs) in Addressing Data Imbalancecited by 1
  23. 2025A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraintscited by 1
  24. 2021A New Distributed Method for Training Generative Adversarial Networkscited by 0
  25. 2021HydraGAN A Multi-head, Multi-objective Approach to Synthetic Data Generationcited by 0
  26. 2022Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Modelscited by 0
  27. 2023GAN-based Vertical Federated Learning for Label Protection in Binary Classificationcited by 0
  28. 2023Distributed Conditional GAN (discGAN) For Synthetic Healthcare Data Generationcited by 0
  29. 2024CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AIcited by 0
  30. 2024FissionVAE: Federated Non-IID Image Generation with Latent Space and Decoder Decompositioncited by 0
  31. 2024FedAT: Federated Adversarial Training for Distributed Insider Threat Detectioncited by 0
  32. 2024Recovering Global Data Distribution Locally in Federated Learningcited by 0
  33. 2024MGMD-GAN: Generalization Improvement of Generative Adversarial Networks with Multiple Generator Multiple Discriminator Framework Against Membership Inference Attackscited by 0
  34. 2024ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networkscited by 0
  35. 2024FedCAR: Cross-client Adaptive Re-weighting for Generative Models in Federated Learningcited by 0
  36. 2025Provably Near-Optimal Federated Ensemble Distillation with Negligible Overheadcited by 0
  37. 2026Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Modelcited by 0