MobileGCN applied to low-dimensional node feature learning

作者：

Highlights：

• This paper proposes a novel Graph Convolutional Networks (GCNs), namely MobileGCN, for semi-supervised learning on graphs represented by low-dimensional node feature space.

• MobileGCN is an extension of MobileNet and MobileNet_v2 for learning graph data. All of them are based on Depth-wise Separable Convolution (DSC).

• Compared with other GCN models, our model performed on graphs of low-dimensional node features has four advantages: Modularization, Expansibility, Reciprocity, and Robustness.

• Performed on three metrics (Accuracy, Macro-f1, and Matthews correlation coefficient (MCC)), Our experiments demonstrate that MobileGCN for graph data can provide state-of-the-art results in both low- and high-dimensional node feature space.

摘要

•This paper proposes a novel Graph Convolutional Networks (GCNs), namely MobileGCN, for semi-supervised learning on graphs represented by low-dimensional node feature space.•MobileGCN is an extension of MobileNet and MobileNet_v2 for learning graph data. All of them are based on Depth-wise Separable Convolution (DSC).•Compared with other GCN models, our model performed on graphs of low-dimensional node features has four advantages: Modularization, Expansibility, Reciprocity, and Robustness.•Performed on three metrics (Accuracy, Macro-f1, and Matthews correlation coefficient (MCC)), Our experiments demonstrate that MobileGCN for graph data can provide state-of-the-art results in both low- and high-dimensional node feature space.

论文关键词：Graph convolutional networks,Affinity-aware encoding,Updater,Depth-wise separable graph convolution,Low-Dimensional node features

论文评审过程：Received 23 January 2020, Revised 16 September 2020, Accepted 7 December 2020, Available online 16 December 2020, Version of Record 23 December 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107788