mlsanityData to 14 Oct 2026

Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach

arXiv 2508.12673 ↗First posted 18 Aug 2025cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative learning, yet data heterogeneity remains a critical challenge. While existing methods achieve progress in addressing data heterogeneity for participating clients, they fail to generalize to non-participating clients with in-domain distribution shifts and resource constraints. To mitigate this issue, we present HyperFedZero, a novel method that dynamically generates specialized models via a hypernetwork conditioned on distribution-aware embeddings. Our approach explicitly incorporates distribution-aware inductive biases into the model's forward pass, extracting robust distribution embeddings using a NoisyEmbed-enhanced extractor with a Balancing Penalty, effectively preventing feature collapse. The hypernetwork then leverages these embeddings to generate specialized models chunk-by-chunk for non-participating clients, ensuring adaptability to their unique data distributions. Extensive experiments on multiple datasets and models demonstrate HyperFedZero's remarkable performance, surpassing competing methods consistently with minimal computational, storage, and communication overhead. Moreover, ablation studies and visualizations further validate the necessity of each component, confirming meaningful adaptations and validating the effectiveness of HyperFedZero.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 69 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

38 of 69 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  7. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  8. 2016HyperNetworkscited by 1,027
  9. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  10. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  11. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  12. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 571
26 more
  1. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  2. 2019Federated Learning with Personalization Layerscited by 541
  3. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  4. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  5. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  6. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  7. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  8. 2019Continual learning with hypernetworkscited by 273
  9. 2021Personalized Federated Learning using Hypernetworkscited by 212
  10. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  11. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  12. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  13. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  14. 2018Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysiscited by 156
  15. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  16. 2022Imbalance Trouble: Revisiting Neural-Collapse Geometrycited by 80
  17. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 64
  18. 2019HyperGAN: A Generative Model for Diverse, Performant Neural Networkscited by 51
  19. 2020Communication-Efficient Federated Learning with Compensated Overlap-FedAvgcited by 31
  20. 2020Structural Patterns and Generative Models of Real-world Hypergraphscited by 29
  21. 2023PeFLL: Personalized Federated Learning by Learning to Learncited by 21
  22. 2024Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generationcited by 9
  23. 2023PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learningcited by 8
  24. 2023Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergencecited by 5
  25. 2025E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizingcited by 3
  26. 2024HyperFedNet: Communication-Efficient Personalized Federated Learning Via Hypernetworkcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ForgeVLA: Federated Vision-Language-Action Learning without Language Annotationscited by 1
  2. 2026Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communicationcited by 0