DISCO: Influence Maximization Meets Network Embedding and Deep Learning

TL;DR

DISCO introduces a novel deep learning framework combining network embedding and reinforcement learning to improve influence maximization in social networks, surpassing traditional sampling-based methods in efficiency and influence spread quality.

Contribution

The paper proposes DISCO, a new paradigm using deep learning for influence maximization, addressing limitations of sampling-based approaches and demonstrating superior performance.

Findings

DISCO outperforms classical algorithms in influence spread quality.

DISCO achieves higher efficiency in influence maximization tasks.

The learned model generalizes well across different networks.

Abstract

Since its introduction in 2003, the influence maximization (IM) problem has drawn significant research attention in the literature. The aim of IM is to select a set of k users who can influence the most individuals in the social network. The problem is proven to be NP-hard. A large number of approximate algorithms have been proposed to address this problem. The state-of-the-art algorithms estimate the expected influence of nodes based on sampled diffusion paths. As the number of required samples have been recently proven to be lower bounded by a particular threshold that presets tradeoff between the accuracy and efficiency, the result quality of these traditional solutions is hard to be further improved without sacrificing efficiency. In this paper, we present an orthogonal and novel paradigm to address the IM problem by leveraging deep learning models to estimate the expected influence. Specifically, we present a novel framework called DISCO that incorporates network embedding and deep reinforcement learning techniques to address this problem. Experimental study on real-world networks demonstrates that DISCO achieves the best performance w.r.t efficiency and influence spread quality compared to state-of-the-art classical solutions. Besides, we also show that the learning model exhibits good generality.