DA-DFGAS:Differentiable Federated Graph Neural Architecture Search with Distribution-Aware Attentive Aggregation

Graph neural networks (GNNs) excel at processing non-Euclidean data, privacy concerns often hinder data sharing, leading to data isolation. Although federated learning (FL) provides a privacy-preserving framework for distributed GNN training, combining FL with GNNs presents challenges such as data heterogeneity and client resource constraints. This paper introduces DA-DFGAS: a federated graph neural network architecture search algorithm that minimises resource consumption while maintaining search flexibility through a directed tree topology and path constraint mechanisms. Additionally, it employs a self-attention joint aggregation mechanism based on predicted probability distribution to adjust the discrepancy between the client and global output distributions. A client selection strategy combined with a global-local two-level objective optimisation balances global consistency and local flexibility. Experimental results demonstrate that DA-DFGAS surpasses existing baseline methods across multiple datasets, achieving an accuracy enhancement of 0.5–3.0\% compared to graph learning baselines and 0.5–5.0\% compared to other federated graph learning baselines.