mlsanityData to 7 Oct 2026

A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning

arXiv 2410.21119 ↗First posted 28 Oct 2024cs.DC cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 28 Oct 2024.

Builds on

28 of 48 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  6. 2021Model-Contrastive Federated Learningcited by 762
  7. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  8. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  9. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  10. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  11. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  12. 2019Model Fusion via Optimal Transportcited by 217
16 more
  1. 2019Data-Free Learning of Student Networkscited by 203
  2. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  3. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  4. 2019Zero-shot Knowledge Transfer via Adversarial Belief Matchingcited by 129
  5. 2019One-Shot Federated Learningcited by 124
  6. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  7. 2021Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learningcited by 111
  8. 2020Distilled One-Shot Federated Learningcited by 108
  9. 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
  10. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
  11. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 76
  12. 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 67
  13. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  14. 2020XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learningcited by 58
  15. 2022Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learningcited by 52
  16. 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boostingcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FedAgentKE: Federated Semantic Knowledge Evolution for Heterogeneous Agentscited by 1
  2. 2026FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregationcited by 0
  3. 2026FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modelingcited by 0