EPINE: Enhanced Proximity Information Network Embedding

TL;DR

EPINE introduces a novel approach to network embedding that redefines high-order proximity and offers scalable computation, improving performance in various network analysis tasks.

Contribution

The paper proposes a new method for defining and calculating high-order proximity in network embedding, addressing accuracy and scalability issues.

Findings

Effective in network reconstruction tasks

Improves link prediction accuracy

Enhances node classification performance

Abstract

Unsupervised homogeneous network embedding (NE) represents every vertex of networks into a low-dimensional vector and meanwhile preserves the network information. Adjacency matrices retain most of the network information, and directly charactrize the first-order proximity. In this work, we devote to mining valuable information in adjacency matrices at a deeper level. Under the same objective, many NE methods calculate high-order proximity by the powers of adjacency matrices, which is not accurate and well-designed enough. Instead, we propose to redefine high-order proximity in a more intuitive manner. Besides, we design a novel algorithm for calculation, which alleviates the scalability problem in the field of accurate calculation for high-order proximity. Comprehensive experiments on real-world network datasets demonstrate the effectiveness of our method in downstream machine learning tasks such as network reconstruction, link prediction and node classification.