Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Abstract
We consider the problem of controlling a partially-observed dynamic process on a graph by a limited number of interventions. This problem naturally arises in contexts such as scheduling virus tests to curb an epidemic; targeted marketing in order to promote a product; and manually inspecting posts to detect fake news spreading on social networks. We formulate this setup as a sequential decision problem over a temporal graph process. In face of an exponential state space, combinatorial action space and partial observability, we design a novel tractable scheme to control dynamical processes on temporal graphs. We successfully apply our approach to two popular problems that fall into our framework: prioritizing which nodes should be tested in order to curb the spread of an epidemic, and influence maximization on a graph.
Keywords
Cite
@article{arxiv.2010.05313,
title = {Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks},
author = {Eli A. Meirom and Haggai Maron and Shie Mannor and Gal Chechik},
journal= {arXiv preprint arXiv:2010.05313},
year = {2021}
}
Comments
ICML 2021