Learning to Infer Structures of Network Games

TL;DR

This paper introduces a transformer-based method to infer network structures in strategic games from equilibrium actions without needing utility functions, demonstrating superior performance on synthetic and real data.

Contribution

The paper presents a novel transformer architecture that infers network structures from game outcomes without requiring utility function knowledge, improving over existing methods.

Findings

Effective inference of network structures from equilibrium actions.

Outperforms existing methods on synthetic and real-world data.

Applicable to various types of network games.

Abstract

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.