2020/12/20 by Yihao Xue, Chaoyue Niu, Xue, Yihao +12 · 2 citations
Computer Science · #Distributed #FOS: Computer and information sciences #G.3 #I.2.6 #Machine Learning (cs.LG) #Mobile Crowdsensing and Crowdsourcing #Parallel #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC) #cs.DC #cs.LG
paper · pdf · doi:10.48550/arxiv.2012.10936
Accepted at AAAI 2021
openalex publication_date 2020/12/20 · arxiv created 2021/04/13 · arxiv updated 2021/04/14 · openalex created_date 2021/07/05 · openalex updated_date 2026/07/28
Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guarantee of the global model, however, it is still unclear how each individual client influences the collaborative training process. In this work, we defined a new notion, called \em Fed-Influence, to quantify this influence over the model parameters, and proposed an effective and efficient algorithm to estimate this metric. In particular, our design satisfies several desirable properties: (1) it requires neither retraining nor retracing, adding only linear computational overhead to clients and the server; (2) it strictly maintains the tenets of federated learning, without revealing any client's local private data; and (3) it works well on both convex and non-convex loss functions, and does not require the final model to be optimal. Empirical results on a synthetic dataset and the FEMNIST dataset demonstrate that our estimation method can approximate Fed-Influence with small bias. Further, we show an application of Fed-Influence in model debugging.