发表机构
Northeastern University; University of Padua（东北大学; 帕多瓦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EFFEKT是一种联邦学习框架，通过双向跨蒸馏策略，结合轻量级客户端代理模型与服务器端基础模型，实现高效的领域特定LoRA适配器训练，在低功耗边缘设备上性能优于基线。
AI 中文摘要
近期的数据保护法规加速了联邦学习（FL）在隐私保护型分布式训练中的应用。然而，不断增长的模型规模对客户端设备提出了巨大的计算需求，限制了FL在资源受限场景中的适用性。我们提出了一种新型多领域联邦学习框架，其中轻量级客户端代理模型与服务器端基础模型（FM）协作，在不共享私有数据的情况下学习新概念。我们的方法EFFEKT支持对领域特定的LoRA适配器进行高效的服务器端训练，同时通过新颖的双向跨蒸馏策略保持FM与代理特征提取器之间的特征空间对齐。在多个真实世界数据集上进行的实验，以及在低功耗边缘设备上的部署结果表明，在大多数考虑的领域中，我们的方法优于最先进的基线，同时在客户端保持轻量级计算。
英文摘要
Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increasing model sizes impose substantial computational demands on client devices, limiting FL applicability in resource-constrained settings. We introduce a novel multi-domain federated learning framework in which lightweight client-side proxy models collaborate with a server-side Foundation Model (FM) to learn new concepts without sharing private data. Our approach, EFFEKT, enables efficient server-side training of domain-specific LoRA adapters while preserving feature-space alignment between the FM and proxy extractors via novel bi-directional cross-distillation strategies. Experiments on multiple real-world datasets and deployments on low-power edge devices demonstrate improvements over state-of-the-art baselines in most considered domains while maintaining lightweight computation at the client side.
Comments12 main content pages, 8 appendix pages; 3 main figures, 9 appendix figures; 8 main tables, 9 appendix tables; 1 main algorithm, 4 appendix algorithms; accepted at TMLR
Journal refTransactions on Machine Learning Research (2026), ISSN 2835-8856
