Proceedings of the AAAI Conference on Artificial Intelligence · 2022 · 75 citations · 31 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningMessage PassingDeep LearningGraph AlgorithmsGraph AnalyticsGraph MiningGraph TheoryGraph-based LearningConvolutional Neural NetworksGraph ClassificationGraph IsomorphismGraph KernelsGraph Neural NetworksInterpretable Neural NetworksMessage Passing Neural NetworksNode Embeddings
Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superior performance. Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the Weisfeiler-Lehman (WL) algorithm in graph isomorphism test. To address the limitations of existing graph kernel and GNN methods, in this paper, we propose a novel GNN framework, termed Kernel Graph Neural Networks (KerGNNs), which integrates graph kernels into the message passing process of GNNs. Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with subgraphs to update node embeddings using graph kernels. In addition, we show that MPNNs can be viewed as special cases of KerGNNs. We apply KerGNNs to multiple graph-related tasks and use cross-validation to make fair comparisons with benchmarks. We show that our method achieves competitive performance compared with existing state-of-the-art methods, demonstrating the potential to increase the representation ability of GNNs. We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.
31
Neural Message Passing for Quantum Chemistry
Justin Gilmer, Samuel S. Schoenholz, Patrick Riley et al. · arXiv (Cornell University) · 2017 · 3K citations · Full text
Weisfeiler-lehman graph kernels
Max Planck Digital Library · 2010 · 1.6K citations · Full text