DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model

TL;DR

This paper introduces DGCNN, a novel graph neural network that uses a Gaussian mixture model to handle disordered graph structures, reducing information loss and improving graph classification and retrieval performance.

Contribution

The paper proposes a disordered graph convolutional layer based on Gaussian mixtures, enabling CNNs to process arbitrary and disordered graph neighborhoods without information loss.

Findings

Outperforms state-of-the-art in graph classification

Effective handling of irregular graph structures

Reduces information loss during graph transformation

Abstract

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of the graph or key node neighborhoods of the graph into the same fixed form. During this transfer process, structural information of the graph can be lost, and some redundant information can be incorporated. To overcome this problem, we propose the disordered graph convolutional neural network (DGCNN) based on the mixed Gaussian model, which extends the CNN by adding a preprocessing layer called the disordered graph convolutional layer (DGCL). The DGCL uses a mixed Gaussian function to realize the mapping between the convolution kernel and the nodes in the neighborhood of the graph. The output of the DGCL is the input of the CNN. We further implement a backward-propagation optimization process of the convolutional layer by which we incorporate the feature-learning model of the irregular node neighborhood structure into the network. Thereafter, the optimization of the convolution kernel becomes part of the neural network learning process. The DGCNN can accept arbitrary scaled and disordered neighborhood graph structures as the receptive fields of CNNs, which reduces information loss during graph transformation. Finally, we perform experiments on multiple standard graph datasets. The results show that the proposed method outperforms the state-of-the-art methods in graph classification and retrieval.