Learning Large-scale Network Embedding from Representative Subgraph

TL;DR

This paper introduces NES, a novel network embedding method that learns from a small representative subgraph, significantly improving efficiency while maintaining comparable performance to existing methods.

Contribution

NES is a new approach that leverages graph sampling theories to efficiently learn network embeddings from a small subgraph, reducing computational costs.

Findings

NES achieves comparable embedding quality to full-network methods.

NES significantly reduces computational time and resources.

Experiments on various networks validate NES's efficiency and effectiveness.

Abstract

We study the problem of large-scale network embedding, which aims to learn low-dimensional latent representations for network mining applications. Recent research in the field of network embedding has led to significant progress such as DeepWalk, LINE, NetMF, NetSMF. However, the huge size of many real-world networks makes it computationally expensive to learn network embedding from the entire network. In this work, we present a novel network embedding method called "NES", which learns network embedding from a small representative subgraph. NES leverages theories from graph sampling to efficiently construct representative subgraph with smaller size which can be used to make inferences about the full network, enabling significantly improved efficiency in embedding learning. Then, NES computes the network embedding from this representative subgraph, efficiently. Compared with well-known methods, extensive experiments on networks of various scales and types demonstrate that NES achieves comparable performance and significant efficiency superiority.