Convolutional Kernel Networks for Graph-Structured Data

Abstract

We introduce a family of multilayer graph kernels and establish new links between graph convolutional neural networks and kernel methods. Our approach generalizes convolutional kernel networks to graph-structured data, by representing graphs as a sequence of kernel feature maps, where each node carries information about local graph substructures. On the one hand, the kernel point of view offers an unsupervised, expressive, and easy-to-regularize data representation, which is useful when limited samples are available. On the other hand, our model can also be trained end-to-end on large-scale data, leading to new types of graph convolutional neural networks. We show that our method achieves competitive performance on several graph classification benchmarks, while offering simple model interpretation. Our code is freely available at https://github.com/claying/GCKN.

References in corpus (6)

• A Survey on Graph Kernels
• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
• Anonymous Walk Embeddings
• RetGK: Graph Kernels based on Return Probabilities of Random Walks
• Pre-training Graph Neural Networks with Kernels
• Recurrent Kernel Networks

Cited by in corpus (8)

• A Comprehensive Survey on Deep Graph Representation Learning
• Graph Kernels: A Survey
• KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
• Iterative Graph Self-Distillation
• Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
• Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
• On Inductive Biases for Machine Learning in Data Constrained Settings