A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures

arXiv:2403.16004v1 Announce Type: new
Abstract: Over the past few years, federated learning has become widely used in various classical machine learning fields because of its collaborative ability to train data from multiple sources without compromising privacy. However, in the area of graph neural networks, the nodes and network structures of graphs held by clients are different in many practical applications, and the aggregation method that directly shares model gradients cannot be directly applied to this scenario. Therefore, this work proposes …

abstract aggregation arxiv become classification collaborative cs.ai cs.lg data federated learning fields graph graph neural networks however machine machine learning multiple network networks neural networks node nodes privacy tasks train type