DeepAI AI Chat
Log In Sign Up

Graph Kernel Neural Networks

by   Luca Cosmo, et al.
Queen Mary University of London
Università Ca' Foscari Venezia

The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be represented as regular grids in the Euclidean space, extending the convolution operator to work on graphs proves more challenging, due to their irregular structure. In this paper, we propose to use graph kernels, i.e., kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type and number of graph kernels and has the added benefit of providing some interpretability in terms of the structural masks that are learned during the training process, similarly to what happens for convolutional masks in traditional convolutional neural networks. We perform an extensive ablation study to investigate the impact of the model hyper-parameters and we show that our model achieves competitive performance on standard graph classification datasets.


page 1

page 2

page 3

page 4


SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

We present Spline-based Convolutional Neural Networks (SplineCNNs), a va...

QESK: Quantum-based Entropic Subtree Kernels for Graph Classification

In this paper, we propose a novel graph kernel, namely the Quantum-based...

SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data

Convolutional Neural Networks have revolutionized vision applications. T...

Generalized Value Iteration Networks: Life Beyond Lattices

In this paper, we introduce a generalized value iteration network (GVIN)...

QDC: Quantum Diffusion Convolution Kernels on Graphs

Graph convolutional neural networks (GCNs) operate by aggregating messag...

Decoupled Networks

Inner product-based convolution has been a central component of convolut...

Graph-Time Convolutional Neural Networks

Spatiotemporal data can be represented as a process over a graph, which ...