Force-directed graph embedding with hops distance

TL;DR

This paper introduces a novel force-directed graph embedding method that uses physical force simulations based on hop distances to produce scalable, topology-preserving node embeddings for graph analysis tasks.

Contribution

It presents a new force-directed embedding approach utilizing steady acceleration formulas and customized forces, enhancing scalability and preserving graph structure.

Findings

Achieves competitive performance on graph analysis tasks.

Method is intuitive, parallelizable, and scalable.

Preserves graph topology and structural features.

Abstract

Graph embedding has become an increasingly important technique for analyzing graph-structured data. By representing nodes in a graph as vectors in a low-dimensional space, graph embedding enables efficient graph processing and analysis tasks like node classification, link prediction, and visualization. In this paper, we propose a novel force-directed graph embedding method that utilizes the steady acceleration kinetic formula to embed nodes in a way that preserves graph topology and structural features. Our method simulates a set of customized attractive and repulsive forces between all node pairs with respect to their hop distance. These forces are then used in Newton's second law to obtain the acceleration of each node. The method is intuitive, parallelizable, and highly scalable. We evaluate our method on several graph analysis tasks and show that it achieves competitive performance compared to state-of-the-art unsupervised embedding techniques.