Node-Feature Convolution for Graph Convolutional Networks

作者：

Highlights：

• A novel strategy to construct a fixed-size feature map via neighbor selection and ordering.

• A new node-feature convolution (NFC) layer for graph convolutional network (GCN).

• Insightful studies on varying aggregators, neighborhood size, and model depth.

• Demonstration of the efficacy of NFC-based GCNs on benchmark datasets.

摘要

•A novel strategy to construct a fixed-size feature map via neighbor selection and ordering.•A new node-feature convolution (NFC) layer for graph convolutional network (GCN).•Insightful studies on varying aggregators, neighborhood size, and model depth.•Demonstration of the efficacy of NFC-based GCNs on benchmark datasets.

论文关键词：Graph,Representation learning,Graph convolutional networks,Convolutional neural networks

论文评审过程：Received 9 July 2020, Revised 15 March 2021, Accepted 19 March 2022, Available online 26 March 2022, Version of Record 9 April 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108661