Nash Welfare in Additively Separable Hedonic Games

TL;DR

This paper explores Nash welfare in additively separable hedonic games, introducing approximation algorithms, analyzing computational complexity, and establishing properties of high Nash welfare partitions.

Contribution

It initiates the study of Nash welfare in ASHGs, providing approximation algorithms, hardness results, and complexity boundaries for various subclasses.

Findings

High Nash welfare partitions guarantee contractual Nash stability in symmetric games.

NP-hardness of maximizing Nash welfare in ASHGs is established, even for symmetric aversion to enemies.

Approximation algorithms with ratios of n-1 and 2n are developed for specific subclasses.

Abstract

Additively separable hedonic games (ASHGs) are a prominent model of coalition formation where agents' preferences are derived from their individual valuations of peers. While social welfare maximization in ASHGs has traditionally focused mostly on utilitarian welfare, Nash welfare -- a well-established metric in economics which balances fairness with efficiency and offers scale invariance -- has been entirely overlooked. In this paper, we initiate the study of Nash welfare in ASHGs. We point out desirable properties fulfilled by partitions with high Nash welfare. This includes guaranteed contractual Nash stability in symmetric games, even for any approximation of Nash welfare. This is particularly appealing since, as for other welfare notions, Nash welfare turns out to be NP-hard to maximize, even for the ASHG subclass of symmetric aversion to enemies games (AEGs). A main focus of our study is on approximation algorithms for the Nash welfare objective. We present packing-based algorithms with approximation ratios for well-established subclasses of ASHGs: $n-1$ for AEGs and $2n$ for appreciation of friends games. This is complemented by a strict inapproximability result showing it is NP-hard to approximate Nash welfare within a factor of $1.0000759$ in general ASHGs. Further, we investigate the restricted settings with an upper bound on the coalition size or number of coalitions, and draw the boundary between the cases admitting efficient algorithms and those yielding NP-hardness: bounding the allowed size or number of coalitions by $2$ admits polynomial-time solvability, whereas bounds of $3$ or more yield NP-hardness or unbounded inapproximability.