AAAI Publications, Thirty-First AAAI Conference on Artificial Intelligence

Font Size: 
On Pareto Optimality in Social Distance Games
Alkida Balliu, Michele Flammini, Dennis Olivetti

Last modified: 2017-02-10

Abstract


We investigate Pareto stability in Social Distance Games, that are coalition forming games in which agents utilities are proportional to their harmonic centralities in the respective coalitions, i.e., to the average inverse distance from the other agents. Pareto optimal solutions have been already considered in the literature as outcomes arising from the strategic interaction of the agents. In particular, they are stable under the deviation of the grand coalition, as they do not permit a simultaneous deviation by all the agents making all of them weakly better off and some strictly better off. We first show that, while computing a Pareto stable solution maximizing the social welfare is NP-hard in bounded degree graphs, a 2 min{Delta,sqrt n}-approximating one can be determined in polynomial time, where n is the number of agents and Delta the maximum node degree. We then determine asymptotically tight bounds on the Price of Pareto Optimality for several classes of social graphs arising from the following combinations: unbounded and bounded node degree, undirected and directed edges, unweighted and weighted edges.

Keywords


Algorithmic Game Theory, Coalition Formation, Social Distance Games, Pareto Stability

Full Text: PDF