DeepAI AI Chat
Log In Sign Up

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

by   Aosong Feng, et al.
Yale University

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.


page 4

page 8

page 9

page 10

page 11

page 12

page 13

page 15


Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm

In recent years, Graph Neural Network (GNN) has bloomly progressed for i...

Graph Anisotropic Diffusion

Traditional Graph Neural Networks (GNNs) rely on message passing, which ...

Pre-training Graph Neural Networks with Kernels

Many machine learning techniques have been proposed in the last few year...

A Novel Higher-order Weisfeiler-Lehman Graph Convolution

Current GNN architectures use a vertex neighborhood aggregation scheme, ...

Statistical Mechanics of Generalization In Graph Convolution Networks

Graph neural networks (GNN) have become the default machine learning mod...

Sparsifying the Update Step in Graph Neural Networks

Message-Passing Neural Networks (MPNNs), the most prominent Graph Neural...

Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks

For learning graph representations, not all detailed structures within a...