Timezone: »

Learning to Infer Structures of Network Games
Emanuele Rossi · Federico Monti · Yan Leng · Michael Bronstein · Xiaowen Dong

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1107

Strategic interactions between a group of individuals or organisations can be modelled as games played on networks, where a player's payoff depends not only on their actions but also on those of their neighbours. Inferring the network structure from observed game outcomes (equilibrium actions) is an important problem with numerous potential applications in economics and social sciences. Existing methods mostly require the knowledge of the utility function associated with the game, which is often unrealistic to obtain in real-world scenarios. We adopt a transformer-like architecture which correctly accounts for the symmetries of the problem and learns a mapping from the equilibrium actions to the network structure of the game without explicit knowledge of the utility function. We test our method on three different types of network games using both synthetic and real-world data, and demonstrate its effectiveness in network structure inference and superior performance over existing methods.

Author Information

Emanuele Rossi (Twitter)
Federico Monti (Fabula AI)
Yan Leng (University of Texas at Austin)

I am a network scientist and computational social science. I am interested in using large-scale data sets, network theory, and machine learning techniques to understand human and organizational behaviors over networks

Michael Bronstein (Imperial College / Twitter)
Xiaowen Dong (Oxford)

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

More from the Same Authors