FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search
This addresses the need for efficient and privacy-preserving neural architecture search in federated learning for graph data, though it appears incremental as it adapts existing NAS techniques to FL settings.
The paper tackles the problem of automatically designing Graph Convolutional Network (GCN) architectures in Federated Learning (FL) scenarios, where existing methods are inefficient and inapplicable due to distributed and private datasets; it proposes FL-AGCNS, which finds better GCN models in short time, surpassing state-of-the-art NAS methods and GCN models.
Recently, some Neural Architecture Search (NAS) techniques are proposed for the automatic design of Graph Convolutional Network (GCN) architectures. They bring great convenience to the use of GCN, but could hardly apply to the Federated Learning (FL) scenarios with distributed and private datasets, which limit their applications. Moreover, they need to train many candidate GCN models from scratch, which is inefficient for FL. To address these challenges, we propose FL-AGCNS, an efficient GCN NAS algorithm suitable for FL scenarios. FL-AGCNS designs a federated evolutionary optimization strategy to enable distributed agents to cooperatively design powerful GCN models while keeping personal information on local devices. Besides, it applies the GCN SuperNet and a weight sharing strategy to speed up the evaluation of GCN models. Experimental results show that FL-AGCNS can find better GCN models in short time under the FL framework, surpassing the state-of-the-arts NAS methods and GCN models.