Boosting Graph Embedding on a Single GPU

TL;DR

GOSH is a GPU-based graph embedding tool that enables large-scale graph embedding with minimal hardware, significantly improving speed and accuracy for link prediction and node classification tasks.

Contribution

Introduces GOSH, a novel GPU-accelerated graph embedding method with a graph coarsening algorithm and decomposition schema for large graphs on a single GPU.

Findings

Embeds a 65 million vertex graph in under 30 minutes on a single GPU.

Achieves state-of-the-art accuracy and speed in link prediction.

Delivers high-quality node embeddings efficiently for large-scale graphs.

Abstract

Graphs are ubiquitous, and they can model unique characteristics and complex relations of real-life systems. Although using machine learning (ML) on graphs is promising, their raw representation is not suitable for ML algorithms. Graph embedding represents each node of a graph as a d-dimensional vector which is more suitable for ML tasks. However, the embedding process is expensive, and CPU-based tools do not scale to real-world graphs. In this work, we present GOSH, a GPU-based tool for embedding large-scale graphs with minimum hardware constraints. GOSH employs a novel graph coarsening algorithm to enhance the impact of updates and minimize the work for embedding. It also incorporates a decomposition schema that enables any arbitrarily large graph to be embedded with a single GPU. As a result, GOSH sets a new state-of-the-art in link prediction both in accuracy and speed, and delivers high-quality embeddings for node classification at a fraction of the time compared to the state-of-the-art. For instance, it can embed a graph with over 65 million vertices and 1.8 billion edges in less than 30 minutes on a single GPU.