RUM: network Representation learning throUgh Multi-level structural information preservation

TL;DR

RUM is a novel network representation learning framework that captures multi-level structural information, including local triads, neighborhood, and global communities, leading to improved performance in real-world tasks.

Contribution

The paper introduces RUM, a flexible framework that explicitly preserves multi-level structural information in network embeddings, extending beyond local structures to include global community features.

Findings

RUM outperforms existing methods in real-life tasks.

Incorporating multi-level structural info improves embedding quality.

Flexible integration with various community detection algorithms.

Abstract

We have witnessed the discovery of many techniques for network representation learning in recent years, ranging from encoding the context in random walks to embedding the lower order connections, to finding latent space representations with auto-encoders. However, existing techniques are looking mostly into the local structures in a network, while higher-level properties such as global community structures are often neglected. We propose a novel network representations learning model framework called RUM (network Representation learning throUgh Multi-level structural information preservation). In RUM, we incorporate three essential aspects of a node that capture a network's characteristics in multiple levels: a node's affiliated local triads, its neighborhood relationships, and its global community affiliations. Therefore the framework explicitly and comprehensively preserves the structural information of a network, extending the encoding process both to the local end of the structural information spectrum and to the global end. The framework is also flexible enough to take various community discovery algorithms as its preprocessor. Empirical results show that the representations learned by RUM have demonstrated substantial performance advantages in real-life tasks.