ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic Set Representations

TL;DR

ProbGraph introduces probabilistic set representations like Bloom filters to enable fast, approximate parallel graph mining with strong theoretical guarantees, significantly improving performance while maintaining high accuracy.

Contribution

It presents a novel graph representation method using probabilistic sets that accelerates parallel graph mining algorithms with theoretical guarantees on efficiency and accuracy.

Findings

Up to 50x speedup over exact baselines on 32 cores

Achieves over 90% accuracy on many datasets

Provides new bounds and algorithms for probabilistic set representations

Abstract

Important graph mining problems such as Clustering are computationally demanding. To significantly accelerate these problems, we propose ProbGraph: a graph representation that enables simple and fast approximate parallel graph mining with strong theoretical guarantees on work, depth, and result accuracy. The key idea is to represent sets of vertices using probabilistic set representations such as Bloom filters. These representations are much faster to process than the original vertex sets thanks to vectorizability and small size. We use these representations as building blocks in important parallel graph mining algorithms such as Clique Counting or Clustering. When enhanced with ProbGraph, these algorithms significantly outperform tuned parallel exact baselines (up to nearly 50x on 32 cores) while ensuring accuracy of more than 90% for many input graph datasets. Our novel bounds and algorithms based on probabilistic set representations with desirable statistical properties are of separate interest for the data analytics community.