Genetic-GNN: Evolutionary architecture search for Graph Neural Networks

Neural architecture search (NAS) has seen significant attention throughout the computational intelligence research community and has pushed forward the state-of-the-art of many neural models to address grid-like data such as texts and images. However, little work has been done on Graph Neural Network (GNN) models dedicated to unstructured network data. Given the huge number of choices and combinations of components such as aggregators and activation functions, determining the suitable GNN model for a specific problem normally necessitates tremendous expert knowledge and laborious trials. In addition, the moderate change of hyperparameters such as the learning rate and dropout rate would dramatically impact the learning capacity of a GNN model. In this paper, we propose a novel framework through the evolution of individual models in a large GNN architecture searching space. Instead of simply optimizing the model structures, an alternating evolution process is performed between GNN model structures and hyperparameters to dynamically approach the optimal fit of each other. Experiments and validations demonstrate that evolutionary NAS is capable of matching existing state-of-the-art reinforcement learning methods for both transductive and inductive graph representation learning and node classification. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

Neural architecture search (NAS) has gained significant attention in computational intelligence research, but there is limited research on Graph Neural Network (GNN) models for unstructured network data. This paper proposes a novel framework that evolves individual models in a large GNN architecture search space to dynamically approach the optimal fit. Experimental results show that evolutionary NAS matches state-of-the-art reinforcement learning methods for graph representation learning and node classification.