Disentangling data distribution for Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) facilitates collaborative training of a global model whose performance is boosted by private data owned by distributed clients, without compromising data privacy. Yet the wide applicability of FL is hindered by entanglement of data distributions across different clients. This paper demonstrates for the first time that by disentangling data distributions FL can in principle achieve efficiencies comparable to those of distributed systems, requiring only one round of communication. To this end, we propose a novel FedDistr algorithm, which employs stable diffusion models to decouple and recover data distributions. Empirical results on the CIFAR100 and DomainNet datasets show that FedDistr significantly enhances model utility and efficiency in both disentangled and near-disentangled scenarios while ensuring privacy, outperforming traditional federated learning methods.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 16 Oct 2024.
Builds on
23 of 41 references.
References · 23
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2022Generative Adversarial Networkscited by 5,627
- 2017Neural Discrete Representation Learningcited by 4,712
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2016Deep Learning with Differential Privacycited by 2,728
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2022Diffusion Models in Vision: A Surveycited by 1,015
- 2021Model-Contrastive Federated Learningcited by 766
11 more
- 2019Federated Learning with Personalization Layerscited by 541
- 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
- 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
- 2019One-Shot Federated Learningcited by 125
- 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 77
- 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
- 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
- 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
- 2022PAC Privacy: Automatic Privacy Measurement and Control of Data Processingcited by 19
- 2024An Edge-Cloud Collaboration Framework for Generative AI Service Provision with Synergetic Big Cloud Model and Small Edge Modelscited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence
- 2026FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning
- 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
- 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation
- 2024Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
- 2022sqSGD: Locally Private and Communication Efficient Federated Learning
- 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
- 2024CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness