A learning-based influence maximization framework for complex networks via K-core hierarchies and reinforcement learning

Waseem Ahmad, Bang Wang

Abstract: Highlights•Proposes a maximum likelihood approach integrating network attributes and topology.•Proposes RL-based framework leveraging K-core hierarchies for influence maximization.•Addresses scalability and redundancy challenges of existing RL-based approaches.•Demonstrates effectiveness with real-world and synthetic networks.•Outperforms state-of-the-art methods in experimental results.