DiFuseR: A Distributed Sketch-based Influence Maximization Algorithm for GPUs

TL;DR

DiFuseR is a distributed GPU algorithm that significantly accelerates influence maximization tasks by optimizing GPU utilization and reducing communication, achieving substantial speedups on large networks.

Contribution

It introduces a novel distributed, sketch-based influence maximization algorithm optimized for multi-GPU systems, improving speed and efficiency over existing methods.

Findings

Achieves up to 8x speedup on 8 GPUs

Runs 3.2x faster on a single GPU compared to baseline

Demonstrates effectiveness on large real-world networks

Abstract

Influence Maximization (IM) aims to find a given number of "seed" vertices that can effectively maximize the expected spread under a given diffusion model. Due to the NP-Hardness of finding an optimal seed set, approximation algorithms are often used for IM. However, these algorithms require a large number of simulations to find good seed sets. In this work, we propose DiFuseR, a blazing-fast, high-quality IM algorithm that can run on multiple GPUs in a distributed setting. DiFuseR is designed to increase GPU utilization, reduce inter-node communication, and minimize overlapping data/computation among the nodes. Based on the experiments with various graphs, containing some of the largest networks available, and diffusion settings, the proposed approach is found to be 3.2x and 12x faster on average on a single GPU and 8 GPUs, respectively. It can achieve up to 8x and 233.7x speedup on the same hardware settings. Furthermore, thanks to its smart load-balancing mechanism, on 8 GPUs, it is on average 5.6x faster compared to its single-GPU performance.