Fast GPU-Based Influence Maximization Within Finite Deadlines via Node-Level Parallelism

Abstract

Influence maximization in the continuous-time domain is a prevalent topic in social media analytics. It relates to the problem of identifying those individuals in a social network, whose endorsement of an opinion will maximize the number of expected follow-ups within a finite time window. This work presents a novel GPU-accelerated algorithm that enables node-parallel estimation of influence spread in the continuous-time domain. Given a finite time window, the method involves decomposing a social graph into multiple local regions within which influence spread can be estimated in parallel to allow for fast and low-cost computations. Experiments show that the proposed method achieves up to x85 speed-up vs. the state-of-the-art on real-world social graphs with up to 100K nodes and 2.5M edges. In addition, our optimization solutions are within 98.9% of the influence spread achieved by current state-of-the-art. The memory consumption of our method is also substantially lower. Indicatively, our method can achieve, on a single GPU, similar running time performance as the state-of-the-art, when the latter distributes execution across hundreds of CPU cores.