mlsanityData to 14 Oct 2026

Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning

arXiv 2508.05157 ↗First posted 7 Aug 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables collaborative training across distributed clients without sharing raw data, offering strong privacy benefits. However, most methods assume all clients remain available throughout training, which is unrealistic as new clients often join over time. We study this setting, where the task and label space stay fixed but clients arrive in batches. Our analysis reveals two key challenges: updating the shared model only with new clients harms existing clients, while freezing it protects them but blocks gains from new knowledge. To capture these trade-offs, we introduce Proactive Adaptation (PA) for onboarding gains and Retroactive Improvement (RI) for changes in earlier clients without retraining. We then propose pFedDSH, which combines a central hypernetwork for personalized initialization, batch-specific binary masks for capacity preservation and allocation, and server-side data-free replay to propagate improvements without exposing client data. Experiments show that pFedDSH preserves stability for existing clients while keeping communication and adaptation costs unchanged for new clients.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

17 of 23 references.

References · 17

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  5. 2019Federated Learning with Personalization Layerscited by 541
  6. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  7. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  8. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  9. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  10. 2021Personalized Federated Learning using Hypernetworkscited by 212
  11. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  12. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
5 more
  1. 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuningcited by 27
  2. 2023PeFLL: Personalized Federated Learning by Learning to Learncited by 21
  3. 2024Federated Continual Learning for Edge-AI: A Comprehensive Surveycited by 11
  4. 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgettingcited by 9
  5. 2024Federated Class-Incremental Learning with New-Class Augmented Self-Distillationcited by 4

Built on by

Not cited yet.