Budgeted Influence Maximization via Boost Simulated Annealing in Social Networks

TL;DR

This paper introduces a boosted simulated annealing algorithm for the budgeted influence maximization problem in social networks, achieving better influence spread with comparable or less computational time.

Contribution

It presents a novel boosted simulated annealing approach with heuristic strategies for efficient influence maximization under budget constraints.

Findings

Outperforms existing algorithms in influence spread

Achieves similar or reduced running time

Effective on both real and synthetic networks

Abstract

Due to much closer to real application scenarios,the budgeted influence maximization (BIM) problem has attracted great attention among researchers. As a variant of the influence maximization (IM) problem, the BIM problem aims at mining several nodes with different costs as seeds with limited budget to maximize the influence as possible. By first activating these seed nodes and spreading influence under the given propagation model, the maximized spread of influence can be reached in the network. Several approaches have been proposed for BIM. Most of them are modified versions of the greedy algorithm, which work well on the IM but seems inefficient for the BIM because huge time consuming is inevitable. Recently, some intelligence algorithms are proposed in order to reduce the running time, but analysis shows that they cannot fully utilize the relationships between nodes in networks, which will result in influence loss. Inspired by this, we propose an efficient method based on boosted simulated annealing (SA) algorithm in this paper. Three heuristic strategies are proposed to improve the performance and speed up the proposed algorithm. Experimental results on both real world and synthetic networks demonstrate that the proposed boosted SA performs much better than existed algorithms on performance with almost equal or less running time.