Attribute2vec: Deep Network Embedding Through Multi-Filtering GCN

TL;DR

This paper introduces Attribute2vec, a multi-filtering GCN framework that enhances network embedding by capturing diverse node features, significantly improving performance especially with limited training data.

Contribution

It proposes a novel multi-filtering GCN approach that outperforms existing attribute embedding methods in network embedding tasks.

Findings

Multi-filtering GCN captures diverse node features effectively.

Significant performance improvements with limited training data.

Outperforms baseline methods in link prediction and node classification.

Abstract

We present a multi-filtering Graph Convolution Neural Network (GCN) framework for network embedding task. It uses multiple local GCN filters to do feature extraction in every propagation layer. We show this approach could capture different important aspects of node features against the existing attribute embedding based method. We also show that with multi-filtering GCN approach, we can achieve significant improvement against baseline methods when training data is limited. We also perform many empirical experiments and demonstrate the benefit of using multiple filters against single filter as well as most current existing network embedding methods for both the link prediction and node classification tasks.