aiqbench analysis
SP-GCRL advances influence maximization by integrating graph contrastive learning with reinforcement learning to handle noisy, incomplete social networks efficiently. This approach addresses critical challenges in modeling non-stationary diffusion dynamics while scaling effectively for large real-world topologies. The method demonstrates significant performance gains over existing baselines without relying on computationally expensive metrics.
SP-GCRL: Influence Maximization on Incomplete Social Graphs
arXiv:2605.12513v2 Announce Type: replace-cross Abstract: Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial observability.We first introduce a social-propagation-aware nonlinear diffusion function to model reinforcement/diminishing effects and probability drift under repeated exposure; we then construct dual structural views and perform contrastive learning to obtain node representations robust to missing edges and weak ties, while replacing expensive strategy metrics with a GAT-based regression surrogate to improve efficiency and scalability; finally, we use DDQN to learn an end-to-end seed selection policy on top of these representations. Experiments on multiple real-world networks show that SP-GCRL achieves significant gains over heuristic and learning-based baselines across budgets and topologies, while maintaining strong large-scale scalability.
Abstract:Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial this http URL first introduce a social-propagation-aware nonlinear diffusion function to model reinforcement/diminishing effects and probability drift under repeated exposure; we then construct dual structural views and perform contrastive learning to obtain node representations robust to missing edges and weak ties, while replacing expensive strategy metrics with a GAT-based regression surrogate to improve efficiency and scalability; finally, we use DDQN to learn an end-to-end seed selection policy on top of these representations. Experiments on multiple real-world networks show that SP-GCRL achieves significant gains over heuristic and learning-based baselines across budgets and topologies, while maintaining strong large-scale scalability.
Accepted by DASFAA 2026. The first two authors contributed equally
Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI)
arXiv:2605.12513 [cs.SI]
(or arXiv:2605.12513v2 [cs.SI] for this version)
https://doi.org/10.48550/arXiv.2605.12513 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 238 words
Related coverage
The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers
arXiv · Jun 12, 2026
Hint-based CoT faithfulness evals still mostly work on Claude
LessWrong · Jul 30, 2026
Graph Neural Networks for Influence Maximization in Social Networks: An Unsupervised Minimum Dominating Set Approach
arXiv · Sep 15, 2026
Social Theory and Agent Foundations
LessWrong · Oct 8, 2026