新用户加入时，模型不遗忘旧用户且无需传数据。
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
- 用超网络+掩码实现个性化初始化与容量分配
- 服务器端无数据回放，提升旧客户性能不重训
- 适合长期新增用户的联邦学习场景
联邦学习（FL）可在不共享原始数据的前提下实现跨客户端协同训练，具有强隐私保护优势。然而，现有方法大多假设所有客户端在整个训练过程中始终可用，这在现实中并不成立——新客户端常以批次形式陆续加入。本文研究这一设定：任务和标签空间保持不变，但客户端分批到来。分析揭示两个关键挑战：仅用新客户端更新共享模型会损害已有客户端表现；而冻结模型虽保护旧客户，却无法吸收新知识。为此，我们提出主动适应（PA）以获取新客户收益，以及被动改进（RI）以优化早期客户表现而不需重训。进一步提出pFedDSH，结合中心超网络实现个性化初始化，使用批次专属二值掩码维持模型容量与分配，通过服务端无数据回放机制传播改进，避免暴露客户数据。实验表明，pFedDSH在保持旧客户稳定性的同时，使新客户通信与适配成本不变。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。