通过正交变换实现黑盒基础模型的泛化与个性化联邦学习
Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations
在视觉任务中，当基础模型（如CLIP）只能黑盒访问时，可通过客户端特定的正交变换适配嵌入，避免梯度冲突并保护知识产权，为联邦场景下的视觉模型个性化提供可复用方案。
原文依据 FedOT employs a shared global task-dependent classifier while facilitating local adaptation through client-specific orthogonal transformations applied externally to the FM embeddings.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习（FL）在保护数据隐私的同时支持去中心化模型训练。然而，在异构（非独立同分布）环境中同时实现鲁棒的泛化和有效的个性化仍然是一项艰巨挑战。此外，专有基础模型（FM）的广泛采用引入了双重隐私的关键需求：（a）保护敏感的客户端数据，（b）保护服务器宝贵的知识产权。这要求对基础模型进行严格的黑盒访问。为应对这些多方面挑战，我们提出了FedOT，一种针对黑盒基础模型优化的新型联邦学习框架。FedOT采用共享的全局任务相关分类器，同时通过在基础模型嵌入外部应用客户端特定的正交变换来促进本地适配。该架构从根本上保证基础模型的内部参数不可访问且不被修改。通过强制正交性，FedOT有效缓解了不同客户端间的梯度冲突（该冲突在理论上是有界的），保持了基础模型表示的语义完整性，并在显著数据异构下实现了鲁棒性能。全局与本地参数的协同最优地平衡了泛化与个性化，在多种基准上显著优于基线联邦学习方法。大量实证分析，包括严格的多随机种子验证和可扩展性评估，证实了FedOT的鲁棒性、高效性和优越性能。
英文原文摘要 1548 字符
Federated Learning (FL) facilitates decentralized model training while preserving data privacy. However, achieving both robust generalization and effective personalization simultaneously in heterogeneous (non-IID) environments remains a formidable challenge. Furthermore, the widespread adoption of proprietary Foundation Models (FMs) introduces a critical requirement for dual privacy: (a) protecting sensitive client data and (b) securing the server's valuable intellectual property. This mandates strictly black-box access to the FM. To address these multifaceted challenges, we introduce FedOT, a novel FL framework optimized for black-box FMs. FedOT employs a shared global task-dependent classifier while facilitating local adaptation through client-specific orthogonal transformations applied externally to the FM embeddings. This architecture inherently guarantees that the FM's internal parameters remain inaccessible and unmodified. By enforcing orthogonality, FedOT effectively mitigates gradient conflicts across diverse clients, which is theoretically bounded, preserves the semantic integrity of the FM representations, and achieves robust performance under significant data heterogeneity. The synergy of global and local parameters optimally balances generalization and personalization, markedly outperforming baseline FL methods across diverse benchmarks. Extensive empirical analysis, including rigorous multi-seed validation and scalability assessments, substantiates the robustness, efficiency, and superior performance of FedOT.