Convolutional Kernel Networks for Graph-Structured Data
This work addresses graph classification for researchers and practitioners, offering an incremental improvement by combining kernel methods with neural networks for better interpretability and regularization.
The authors tackled the problem of graph classification by introducing multilayer graph kernels that bridge graph convolutional neural networks and kernel methods, achieving competitive performance on several benchmarks.
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.