A General Framework for Content-enhanced Network Representation Learning

TL;DR

This paper introduces CENE, a network embedding framework that jointly models network structure and node content, improving node classification performance over existing methods by leveraging rich content information.

Contribution

The paper presents a novel framework that integrates content information into network embedding, enhancing the quality of node representations compared to structure-only methods.

Findings

CENE outperforms existing network embedding methods in node classification tasks.

Joint modeling of structure and content improves embedding quality.

Content information significantly benefits network representation learning.

Abstract

This paper investigates the problem of network embedding, which aims at learning low-dimensional vector representation of nodes in networks. Most existing network embedding methods rely solely on the network structure, i.e., the linkage relationships between nodes, but ignore the rich content information associated with it, which is common in real world networks and beneficial to describing the characteristics of a node. In this paper, we propose content-enhanced network embedding (CENE), which is capable of jointly leveraging the network structure and the content information. Our approach integrates text modeling and structure modeling in a general framework by treating the content information as a special kind of node. Experiments on several real world net- works with application to node classification show that our models outperform all existing network embedding methods, demonstrating the merits of content information and joint learning.