Neighborhood Adaptive Graph Convolutional Network for Node Classification

Peiliang Gong

doi:10.1109/ACCESS.2019.2955487

2019-01-01

Peiliang Gong

Lihua Ai *

DOI：10.1109/ACCESS.2019.2955487

原文链接

查看原文

摘要

En 中文

Recently, graph convolutional neural network as an efficient and effective method has experienced significant attention and becomes the de facto method for learning node or graph representations. However, existing most methods use a fixed-order neighborhood information when integrating node representations for node classification on the graph. In this paper, we present a neighborhood adaptive graph convolutional network (NAGCN), a novel method to efficiently learn each nodes representations. Particularly, we construct a convolutional kernel abstracted from the diffusion process, named as the neighborhood adaptive kernel to more precisely learn and integrate related neighborhood node information for each node. As a result, our proposed method can learn more useful information across the relevant near and distant neighbors according to the real applications. We also adopt a threshold mechanism on the constructed kernel to better reserve the most impact neighbor vertices for each node on the graph. Besides, one learnable feature refinement process is used in the model to obtain high-level node representations with sufficient expressive power. The model is also theoretically analyzed in terms of spectral convolution and message passing algorithm. Notably, extensive experiments demonstrate that our method can achieve better performance on node classification tasks compared to other related approaches.

Keyword:

Convolution

Kernel

Task analysis

Adaptation models

Laplace equations

Adaptive systems

Convolutional neural nets

Node classification

graph data

spectral convolution

semi-supervised learning