NodeSig: Binary Node Embeddings via Random Walk Diffusion

TL;DR

NodeSig is a scalable method for generating binary node embeddings using random walk diffusion, balancing efficiency and accuracy for large network analysis tasks.

Contribution

It introduces a novel binary embedding approach leveraging random walk diffusion and stable random projections, improving scalability while maintaining accuracy.

Findings

Achieves comparable accuracy to existing models on node classification.

Demonstrates significant efficiency gains on large networks.

Balances trade-off between computational cost and embedding quality.

Abstract

Graph Representation Learning (GRL) has become a key paradigm in network analysis, with a plethora of interdisciplinary applications. As the scale of networks increases, most of the widely used learning-based graph representation models also face computational challenges. While there is a recent effort toward designing algorithms that solely deal with scalability issues, most of them behave poorly in terms of accuracy on downstream tasks. In this paper, we aim to study models that balance the trade-off between efficiency and accuracy. In particular, we propose NodeSig, a scalable model that computes binary node representations. NodeSig exploits random walk diffusion probabilities via stable random projections towards efficiently computing embeddings in the Hamming space. Our extensive experimental evaluation on various networks has demonstrated that the proposed model achieves a good balance between accuracy and efficiency compared to well-known baseline models on the node classification and link prediction tasks.