Forming Probably Stable Communities with Limited Interactions

A community needs to be partitioned into disjoint groups; each community member has an underlying preference over the groups that they would want to be a member of. We are interested in finding a stable community structure: one where no subset of members $S$ wants to deviate from the current structure. We model this setting as a hedonic game, where players are connected by an underlying interaction network, and can only consider joining groups that are connected subgraphs of the underlying graph. We analyze the relation between network structure, and one's capability to infer statistically stable (also known as PAC stable) player partitions from data. We show that when the interaction network is a forest, one can efficiently infer PAC stable coalition structures. Furthermore, when the underlying interaction graph is not a forest, efficient PAC stabilizability is no longer achievable. Thus, our results completely characterize when one can leverage the underlying graph structure in order to compute PAC stable outcomes for hedonic games. Finally, given an unknown underlying interaction network, we show that it is NP-hard to decide whether there exists a forest consistent with data samples from the network.

[1]  Peter L. Bartlett,et al.  Neural Network Learning - Theoretical Foundations , 1999 .

[2]  Edith Elkind,et al.  Hedonic Games with Graph-restricted Communication , 2016, AAMAS.

[3]  Gabrielle Demange,et al.  On Group Stability in Hierarchies and Networks , 2004, Journal of Political Economy.

[4]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

[5]  Milind Tambe,et al.  Learning Adversary Behavior in Security Games: A PAC Model Perspective , 2015, AAMAS.

[6]  Edith Elkind,et al.  Simple Causes of Complexity in Hedonic Games , 2015, IJCAI.

[7]  Vincent Conitzer,et al.  Combinatorial Auctions with Structured Item Graphs , 2004, AAAI.

[8]  Amnon Shashua,et al.  Introduction to Machine Learning: Class Notes 67577 , 2009, ArXiv.

[9]  Roger B. Myerson,et al.  Graphs and Cooperation in Games , 1977, Math. Oper. Res..

[10]  Matthew O. Jackson,et al.  The Stability of Hedonic Coalition Structures , 2002, Games Econ. Behav..

[11]  Maria-Florina Balcan,et al.  Learning Combinatorial Functions from Pairwise Comparisons , 2016, COLT.

[12]  Éva Tardos,et al.  Algorithm design , 2005 .

[13]  Paul W. Goldberg,et al.  Learning equilibria of games via payoff queries , 2013, EC '13.

[14]  P. Bartlett,et al.  Learning Hedonic Games , 2017 .

[15]  Haris Aziz,et al.  Existence of stability in hedonic coalition formation games , 2012, AAMAS.

[16]  Tim Roughgarden,et al.  Learning Simple Auctions , 2016, COLT.

[17]  Maria-Florina Balcan,et al.  Learning Cooperative Games , 2015, IJCAI.

[18]  Adrian Vetta,et al.  Coalition Games on Interaction Graphs: A Horticultural Perspective , 2015, EC.

[19]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[20]  Rahul Savani,et al.  Computing Stable Outcomes in Hedonic Games , 2010, SAGT.

[21]  Maria-Florina Balcan,et al.  Learning Valuation Functions , 2011, COLT.

[22]  Michael Dom,et al.  Algorithimic Aspects of the Consecutive-Ones Property , 2009, Bull. EATCS.

[23]  Stephan Olariu,et al.  The ultimate interval graph recognition algorithm? , 1998, SODA '98.

[24]  Wen-Lian Hsu,et al.  Fast and Simple Algorithms for Recognizing Chordal Comparability Graphs and Interval Graphs , 1999, SIAM J. Comput..

[25]  D. R. Fulkerson,et al.  Incidence matrices and interval graphs , 1965 .

[26]  Tayfun Sönmez,et al.  Core in a simple coalition formation game , 2001, Soc. Choice Welf..

[27]  Kurt Mehlhorn,et al.  Certifying algorithms for recognizing interval graphs and permutation graphs , 2003, SODA '03.

[28]  Milind Tambe,et al.  Security and Game Theory - Algorithms, Deployed Systems, Lessons Learned , 2011 .

[29]  Dominik Peters,et al.  Graphical Hedonic Games of Bounded Treewidth , 2016, AAAI.

[30]  Sergei Vassilvitskii,et al.  Statistical Cost Sharing , 2017, NIPS.

[31]  Rahul Savani,et al.  Hedonic Games , 2016, Handbook of Computational Social Choice.

[32]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[33]  Evangelos Markakis,et al.  Characteristic function games with restricted agent interactions: Core-stability and coalition structures , 2016, Artif. Intell..

[34]  Kellogg S. Booth,et al.  Testing for the Consecutive Ones Property, Interval Graphs, and Graph Planarity Using PQ-Tree Algorithms , 1976, J. Comput. Syst. Sci..

[35]  J. Sliwinski,et al.  1 2 N ov 2 01 8 Forming Probably Stable Communities with Limited Interactions , 2018 .

[36]  Gerhard J. Woeginger,et al.  Core Stability in Hedonic Coalition Formation , 2012, SOFSEM.

[37]  Laurent Viennot,et al.  Lex-BFS and partition refinement, with applications to transitive orientation, interval graph recognition and consecutive ones testing , 2000, Theor. Comput. Sci..

[38]  Rolf H. Möhring,et al.  A Simple Linear -TIme Algorithm to Recognize Interval Graphs , 1986, WG.

[39]  Edith Elkind,et al.  Bounding the Cost of Stability in Games over Interaction Networks , 2013, AAAI.

[40]  Umesh V. Vazirani,et al.  An Introduction to Computational Learning Theory , 1994 .

[41]  Maria-Florina Balcan,et al.  A General Theory of Sample Complexity for Multi-Item Profit Maximization , 2017, EC.

[42]  Gerhard J. Woeginger,et al.  Two hardness results for core stability in hedonic coalition formation games , 2013, Discret. Appl. Math..