Personalized Federated Learning With Graph
This work addresses the challenge of inefficient knowledge sharing in federated learning for domains like traffic and image analysis, though it appears incremental by building on existing personalized federated learning methods.
The paper tackles the problem of improving knowledge sharing in personalized federated learning by incorporating graph-based structural information among clients, resulting in a novel structured federated learning framework that simultaneously learns global and personalized models and demonstrates effectiveness on traffic and image benchmark datasets.
Knowledge sharing and model personalization are two key components in the conceptual framework of personalized federated learning (PFL). Existing PFL methods focus on proposing new model personalization mechanisms while simply implementing knowledge sharing by aggregating models from all clients, regardless of their relation graph. This paper aims to enhance the knowledge-sharing process in PFL by leveraging the graph-based structural information among clients. We propose a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data. We cast SFL with graph into a novel optimization problem that can model the client-wise complex relations and graph-based structural topology by a unified framework. Moreover, in addition to using an existing relation graph, SFL could be expanded to learn the hidden relations among clients. Experiments on traffic and image benchmark datasets can demonstrate the effectiveness of the proposed method. All implementation codes are available on Github