Force2Vec: Parallel force-directed graph embedding

TL;DR

Force2Vec is a highly parallel graph embedding algorithm based on force-directed layout models, significantly faster than existing methods and effective for visualization and machine learning tasks on large graphs.

Contribution

We introduce Force2Vec, a parallel graph embedding method leveraging force-directed models, achieving substantial speedups and improved performance in visualization and ML tasks.

Findings

43x faster than DeepWalk on average

Can embed graphs with billions of edges in hours

Performs well in visualization and ML tasks

Abstract

A graph embedding algorithm embeds a graph into a low-dimensional space such that the embedding preserves the inherent properties of the graph. While graph embedding is fundamentally related to graph visualization, prior work did not exploit this connection explicitly. We develop Force2Vec that uses force-directed graph layout models in a graph embedding setting with an aim to excel in both machine learning (ML) and visualization tasks. We make Force2Vec highly parallel by mapping its core computations to linear algebra and utilizing multiple levels of parallelism available in modern processors. The resultant algorithm is an order of magnitude faster than existing methods (43x faster than DeepWalk, on average) and can generate embeddings from graphs with billions of edges in a few hours. In comparison to existing methods, Force2Vec is better in graph visualization and performs comparably or better in ML tasks such as link prediction, node classification, and clustering. Source code is available at https://github.com/HipGraph/Force2Vec.