Timezone: »

 
Spotlight
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Eli Meirom · Haggai Maron · Shie Mannor · Gal Chechik

Tue Jul 20 06:35 AM -- 06:40 AM (PDT) @
in Deep Learning Algorithms 2 »

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: Deep Learning

Author Information

Eli Meirom (NVIDIA Research)
Haggai Maron (NVIDIA Research)

I am a Research Scientist at NVIDIA Research. My main fields of interest are machine learning, optimization, and shape analysis. More specifically, I am working on applying deep learning to irregular domains (e.g., graphs, point clouds, and surfaces) and graph/shape matching problems. I completed my Ph.D. in 2019 at the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science under the supervision of Prof. Yaron Lipman.

Shie Mannor (Technion)
Gal Chechik (NVIDIA / Bar-Ilan University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors