Heterogeneous Influence Maximization in User Recommendation

2025-08-19

AI Summary

Existing user recommendation systems struggle to jointly optimize candidates’ propagation potential and interaction willingness: conventional recommendation methods neglect propagation capability modeling, while influence maximization approaches ignore interaction intent. To address this, we propose HeteroIR and HeteroIM—two novel models that, for the first time, jointly model propagation capability and interaction willingness on heterogeneous graphs. We further design an incremental recommendation ranking mechanism based on Reverse Reachable Sets (RIS), enabling efficient co-optimization via two-stage propagation gain estimation, RIS sampling, influence increment computation, and dynamic re-ranking. In A/B tests conducted on Tencent’s online gaming platform, HeteroIR and HeteroIM achieve statistically significant improvements in information diffusion efficiency—8.5% and 10.0% respectively (p < 0.05)—outperforming all baseline methods.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Web Mining and Content Analysis: Content-based information diffusion
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

User recommendation systems enhance user engagement by encouraging users to act as inviters to interact with other users (invitees), potentially fostering information propagation. Conventional recommendation methods typically focus on modeling interaction willingness. Influence-Maximization (IM) methods focus on identifying a set of users to maximize the information propagation. However, existing methods face two significant challenges. First, recommendation methods fail to unleash the candidates' spread capability. Second, IM methods fail to account for the willingness to interact. To solve these issues, we propose two models named HeteroIR and HeteroIM. HeteroIR provides an intuitive solution to unleash the dissemination potential of user recommendation systems. HeteroIM fills the gap between the IM method and the recommendation task, improving interaction willingness and maximizing spread coverage. The HeteroIR introduces a two-stage framework to estimate the spread profits. The HeteroIM incrementally selects the most influential invitee to recommend and rerank based on the number of reverse reachable (RR) sets containing inviters and invitees. RR set denotes a set of nodes that can reach a target via propagation. Extensive experiments show that HeteroIR and HeteroIM significantly outperform the state-of-the-art baselines with the p-value < 0.05. Furthermore, we have deployed HeteroIR and HeteroIM in Tencent's online gaming platforms and gained an 8.5% and 10% improvement in the online A/B test, respectively. Implementation codes are available at https://github.com/socialalgo/HIM.

Problem

• Bridging interaction willingness and information propagation in user recommendation
• Maximizing spread coverage while ensuring user engagement in recommendations
• Addressing the gap between influence maximization and recommendation tasks

Innovation

• Two-stage framework estimates spread profits
• Incrementally selects influential invitees using RR sets
• Reranks recommendations based on reverse reachable sets