SSNE: Effective Node Representation for Link Prediction in Sparse Networks

TL;DR

This paper introduces SSNE, a novel node embedding method designed specifically for link prediction in sparse networks, demonstrating superior performance over existing models through extensive experiments.

Contribution

The paper proposes a new graph embedding model, SSNE, tailored for sparse networks, transforming adjacency matrices into feature representations via a neural network with proven SVD equivalence.

Findings

SSNE outperforms structural similarity indexes in link prediction tasks.

SSNE achieves better results than matrix optimization and other graph embedding models.

The method is validated on both synthetic and real sparse networks.

Abstract

Graph embedding is gaining its popularity for link prediction in complex networks and achieving excellent performance. However, limited work has been done in sparse networks that represent most of real networks. In this paper, we propose a model, Sparse Structural Network Embedding (SSNE), to obtain node representation for link predication in sparse networks. The SSNE first transforms the adjacency matrix into the Sum of Normalized $H$-order Adjacency Matrix (SNHAM), and then maps the SNHAM matrix into a $d$-dimensional feature matrix for node representation via a neural network model. The mapping operation is proved to be an equivalent variation of singular value decomposition. Finally, we calculate nodal similarities for link prediction based on such feature matrix. By extensive testing experiments bases on synthetic and real sparse network, we show that the proposed method presents better link prediction performance in comparison of those of structural similarity indexes, matrix optimization and other graph embedding models.