Diffusion Maps for Textual Network Embedding

TL;DR

The paper introduces DMTE, a novel method for textual network embedding that incorporates global graph structure via diffusion maps, improving semantic relatedness capture and outperforming existing methods in classification and prediction tasks.

Contribution

It presents a diffusion map-based approach for textual network embedding that effectively captures high-order proximity and global structure, which was not addressed by prior models.

Findings

Outperforms state-of-the-art methods in vertex classification.

Achieves better link prediction accuracy.

Effectively captures semantic relatedness through diffusion maps.

Abstract

Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research exploits the relationship of texts on the same edge to graphically embed text. However, these models neglect to measure the complete level of connectivity between any two texts in the graph. We present diffusion maps for textual network embedding (DMTE), integrating global structural information of the graph to capture the semantic relatedness between texts, with a diffusion-convolution operation applied on the text inputs. In addition, a new objective function is designed to efficiently preserve the high-order proximity using the graph diffusion. Experimental results show that the proposed approach outperforms state-of-the-art methods on the vertex-classification and link-prediction tasks.