Federated Learning with Limited Node Labels

TL;DR

This paper introduces FedMpa, a federated learning framework for graph neural networks that effectively learns cross-subgraph node representations with limited labeled data, improving node classification accuracy.

Contribution

The paper proposes FedMpa, a novel SFL framework that addresses missing cross-subgraph edges and reduces label requirements, enhancing federated GNN performance.

Findings

FedMpa outperforms existing methods on six graph datasets.

FedMpa effectively learns cross-subgraph node representations.

Ablation studies confirm the importance of each component.

Abstract

Subgraph federated learning (SFL) is a research methodology that has gained significant attention for its potential to handle distributed graph-structured data. In SFL, the local model comprises graph neural networks (GNNs) with a partial graph structure. However, some SFL models have overlooked the significance of missing cross-subgraph edges, which can lead to local GNNs being unable to message-pass global representations to other parties' GNNs. Moreover, existing SFL models require substantial labeled data, which limits their practical applications. To overcome these limitations, we present a novel SFL framework called FedMpa that aims to learn cross-subgraph node representations. FedMpa first trains a multilayer perceptron (MLP) model using a small amount of data and then propagates the federated feature to the local structures. To further improve the embedding representation of nodes with local subgraphs, we introduce the FedMpae method, which reconstructs the local graph structure with an innovation view that applies pooling operation to form super-nodes. Our extensive experiments on six graph datasets demonstrate that FedMpa is highly effective in node classification. Furthermore, our ablation experiments verify the effectiveness of FedMpa.