FedLEKE: Federated Locate-then-Edit Knowledge Editing for Multi-Client Collaboration

摘要

Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns.To address these challenges, we introduce \textbf{Fed}erated \textbf{L}ocate-then-\textbf{E}dit \textbf{K}nowledge \textbf{E}diting (FedLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse.In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FedLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations.Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96% of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FedLEKE task with our FedEdit framework. Our code is available at https://github.com/zongkaiz/FedLEKE.