Billion-scale Network Embedding with Iterative Random Projection

TL;DR

This paper introduces RandNE, a scalable network embedding method using iterative random projection that efficiently handles billion-scale networks while preserving high-order proximities and supporting dynamic updates.

Contribution

The paper presents a novel iterative random projection approach for billion-scale network embedding that is computationally efficient, distributed-friendly, and capable of dynamic network updates.

Findings

Outperforms state-of-the-art methods in network reconstruction, link prediction, and node classification.

Efficiently handles networks with billions of nodes and edges.

Supports dynamic network updates without error accumulation.

Abstract

Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently. However, the existing methods are incapable of handling billion-scale networks, because they are computationally expensive and, at the same time, difficult to be accelerated by distributed computing schemes. To address these problems, we propose RandNE (Iterative Random Projection Network Embedding), a novel and simple billion-scale network embedding method. Specifically, we propose a Gaussian random projection approach to map the network into a low-dimensional embedding space while preserving the high-order proximities between nodes. To reduce the time complexity, we design an iterative projection procedure to avoid the explicit calculation of the high-order proximities. Theoretical analysis shows that our method is extremely efficient, and friendly to distributed computing schemes without any communication cost in the calculation. We also design a dynamic updating procedure which can efficiently incorporate the dynamic changes of the networks without error aggregation. Extensive experimental results demonstrate the efficiency and efficacy of RandNE over state-of-the-art methods in several tasks including network reconstruction, link prediction and node classification on multiple datasets with different scales, ranging from thousands to billions of nodes and edges.