一句话：提出 TraceFL，通过神经元溯源定位联邦学习中影响全局模型预测的客户端。
联邦学习中，客户端用本地数据训练模型并向中心服务器发送更新，服务器融合为全局模型，但难以将全局模型预测归因到具体客户端。现有 ML 调试方法面向单模型集中式训练，无法直接适用。TraceFL 提出细粒度神经元溯源机制，追踪信息从各客户端流向全局模型的过程：针对给定预测动态量化全局模型神经元的重要性，找出最关键神经元，再映射到每个参与客户端的对应神经元，从而判断贡献并定位责任客户端。作者在六个数据集（含两个真实医学影像数据集）和四个神经网络（含 GPT）上评估，在图像与文本分类的 FL 任务中定位责任客户端准确率达 99%。
In Federated Learning, clients train models on local data and send updates to a central server, which aggregates them into a global model using a fusion algorithm. This collaborative yet privacy-preserving training comes at a cost. FL developers face significant challenges in attributing global model predictions to specific clients. Localizing responsible clients is a crucial step towards (a) excluding clients primarily responsible for incorrect predictions and (b) encouraging clients who contributed highquality models to continue participating in the future. Existing ML debugging approaches are inherently inapplicable as they are designed for single-model, centralized training. We introduce TraceFL, a fine-grained neuron provenance capturing mechanism that identifies clients responsible for a global model's prediction by tracking the flow of information from individual clients to the global model. Since inference on different inputs activates a different set of neurons of the global model, TraceFL dynamically quantifies the significance of the global model's neurons in a given prediction, identifying the most crucial neurons in the global model. It then maps them to the corresponding neurons in every participating client to determine each client's contribution, ultimately localizing the responsible client. We evaluate TraceFL on six datasets, including two real-world medical imaging datasets and four neural networks, including advanced models such as GPT. TraceFL achieves 99% accuracy in localizing the responsible client in FL tasks spanning both image and text classification tasks. At a time when state-of-the-art ML debugging approaches are mostly domain-specific (e.g., image classification only), TraceFL is the first technique to enable highly accurate automated reasoning across a wide range of FL applications.
DOI 原文 ·
@inproceedings{paperbot8860,
title = {TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance},
author = {Waris Gill and Ali Anwar and Muhammad Ali Gulzar},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00128}
}