Graph Embedding with Rich Information through Heterogeneous Network

TL;DR

This paper introduces a novel graph embedding framework that leverages rich node and edge information via a bipartite heterogeneous network and biased random walks, significantly improving classification performance.

Contribution

It presents a general representation learning method for graphs with rich text info using a bipartite heterogeneous network and a biased random walk approach.

Findings

Improves Micro-F1 and Macro-F1 by 10% and 7% on Cora dataset.

Demonstrates effectiveness through extensive experiments.

Outperforms several baseline methods.

Abstract

Graph embedding has attracted increasing attention due to its critical application in social network analysis. Most existing algorithms for graph embedding only rely on the typology information and fail to use the copious information in nodes as well as edges. As a result, their performance for many tasks may not be satisfactory. In this paper, we proposed a novel and general framework of representation learning for graph with rich text information through constructing a bipartite heterogeneous network. Specially, we designed a biased random walk to explore the constructed heterogeneous network with the notion of flexible neighborhood. The efficacy of our method is demonstrated by extensive comparison experiments with several baselines on various datasets. It improves the Micro-F1 and Macro-F1 of node classification by 10% and 7% on Cora dataset.