Network discovery using Reinforcement Learning

A serious challenge when finding influential actors in real-world social networks is the lack of knowledge about the structure of the underlying network. Current state-of-the-art methods rely on hand-crafted sampling algorithms to sample nodes in a carefully constructed order and choose opinion leaders from this discovered network to maximize influence spread in the complete network. In this work, we propose a deep reinforcement learning framework graph neural network modules for network discovery that automatically learns useful node and graph representations that encode important structural properties of the network. At training time, the method identifies portions of the network such that the nodes selected from this sampled subgraph can effectively influence nodes in the complete network. The learned policy can be directly applied on unseen graphs of similar domain. We experiment with real-world social networks and show that the policies learned by our RL agent provide a 7-23% improvement over the current state-ofthe-art method.