Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning

Careful client selection for aggregation can help improve the global model's performance. However, existing research on federated heterogeneous graph learning (FHGL) has paid limited attention to the client selection (CS) problem. Current CS algorithms struggle to accurately assess client contributions and select suitable participants in FHGL, creating a trade-off between convergence and accuracy. In this paper, we propose a Reinforcement Active client selection based Federated Heterogeneous Graph Learning (RAFHGL), which precisely evaluates the importance of local heterogeneous graph data and selects high-contributing clients for aggregation. RAFHGL employs an active learning agent to select representative nodes for local training. The statistical features of the active scores are used to assess client contributions. A client selection agent then chooses clients conducive to global model convergence for aggregation. To address heterogeneity introduced by sample and client selection, the training process stabilizes by correcting local losses based on data prototypes. Experimental results on 4 publicly available heterogeneous graph datasets show that RAFHGL outperforms existing Client Selection algorithms in federated heterogeneous graph learning scenarios in terms of performance and convergence.