E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification

arXiv:2405.03401v1 Announce Type: new
Abstract: This work studies ensemble learning for graph neural networks (GNNs) under the popular semi-supervised setting. Ensemble learning has shown superiority in improving the accuracy and robustness of traditional machine learning by combining the outputs of multiple weak learners. However, adopting a similar idea to integrate different GNN models is challenging because of two reasons. First, GNN is notorious for its poor inference ability, so naively assembling multiple GNN models would deteriorate the inference efficiency. Second, …

abstract accuracy arxiv classification cs.ai cs.lg ensemble gnns graph graph neural network graph neural networks however improving machine machine learning multiple network networks neural network neural networks popular robustness semi semi-supervised studies traditional machine learning type work