Abstract
Arbitrary cost-sharing is a model in which the players of a resource selection game get to declare the payments that they will make, rather than have the payments be determined by a cost-sharing protocol. Arbitrary cost-sharing has been studied in various contexts, such as congestion games, network design games, and scheduling games. The natural counterpart of arbitrary cost-sharing in the context of a utility game is arbitrary utility-sharing, meaning that each player will request a certain utility as a reward for her efforts in generating welfare for the system. This concept has received much less attention in the literature. In this paper, we initiate the study of arbitrary sharing in utility games, placing emphasis on the special case of federated learning utility games, in which players form groups that jointly execute a learning task and each player contributes certain types of data to each group. We present results on the price of anarchy and price of stability, showing that the price of anarchy is 2 and that arbitrary utility sharing is the only known method to achieve price of stability 1 with budget-balanced payments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anshelevich, E., Caskurlu, B.: Exact and approximate equilibria for optimal group network formation. Theor. Comput. Sci. 412(39), 5298–5314 (2011)
Anshelevich, E., Caskurlu, B.: Price of stability in survivable network design. Theory Comput. Syst. 49(1), 98–138 (2011)
Anshelevich, E., Dasgupta, A., Tardos, É., Wexler, T.: Near-optimal network design with selfish agents. Theory Comput. 4(1), 77–109 (2008)
Anshelevich, E., Karagiozova, A.: Terminal backup, 3d matching, and covering cubic graphs. SIAM J. Comput. 40(3), 678–708 (2011)
Bachrach, Y., Syrgkanis, V., Vojnovic, M.: Incentives and efficiency in uncertain collaborative environments. In: WINE, pp. 26–39 (2013)
Calinescu, G., Chekuri, C., Pal, M., Vondrak, J.: Maximizing a submodular set function subject to a matroid constraint (extended abstract). In: IPCO, pp. 182–196 (2007)
Cardinal, J., Hoefer, M.: Non-cooperative facility location and covering games. Theor. Comput. Sci. 411(16–18), 1855–1876 (2010)
Donahue, K., Kleinberg, J.M.: Model-sharing games: analyzing federated learning under voluntary participation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, pp. 5303–5311. AAAI Press (2021)
Donahue, K., Kleinberg, J.M.: Optimality and stability in federated learning: a game-theoretic approach. In: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6–14 December 2021, virtual, pp. 1287–1298 (2021)
Epstein, A., Feldman, M., Mansour, Y.: Strong equilibrium in cost sharing connection games. Games Econ. Behav. 67(1), 51–68 (2009)
Filmus, Y., Ward, J.: The power of local search: maximum coverage over a matroid. In: STACS, pp. 601–612 (2012)
Filmus, Y., Ward, J.: Monotone submodular maximization over a matroid via non-oblivious local search. SIAM J. Comput. 43(2), 514–542 (2014)
Georgoulaki, E., Kollias, K., Tamir, T.: Equilibrium inefficiency in resource buying games with load-dependent costs. In: Algorithmic Game Theory - 13th International Symposium, SAGT 2020, Augsburg, Germany, 16–18 2020 September, Proceedings (2020)
Georgoulaki, E., Kollias, K.: On the price of anarchy of cost-sharing in real-time scheduling systems. In: Web and Internet Economics - 15th International Conference, WINE 2019, New York, NY, USA, 10–12 December 2019, Proceedings (2019)
Georgoulaki, E., Kollias, K., Tamir, T.: Equilibrium inefficiency and computation in cost-sharing games in real-time scheduling systems. Algorithms 14(4), 103 (2021)
Gollapudi, S., Kollias, K., Panigrahi, D., Pliatsika, V.: Profit sharing and efficiency in utility games. In: ESA (2017)
Harks, T., Miller, K.: The worst-case efficiency of cost sharing methods in resource allocation games. Oper. Res. 59(6), 1491–1503 (2011)
Harks, T., Peis, B.: Resource buying games. Algorithmica 70(3), 493–512 (2014)
Hoefer, M.: Non-cooperative tree creation. Algorithmica 53(1), 104–131 (2009)
Hoefer, M.: Competitive cost sharing with economies of scale. Algorithmica 60(4), 743–765 (2011)
Hoefer, M.: Strategic cooperation in cost sharing games. Int. J. Game Theory 42(1), 29–53 (2013)
Marden, J.R., Roughgarden, T.: Generalized efficiency bounds in distributed resource allocation. In: CDC, pp. 2233–2238. IEEE (2010)
Marden, J.R., Wierman, A.: Distributed welfare games. Oper. Res. 61(1), 155–168 (2013)
Tamir, T.: Cost-sharing games in real-time scheduling systems. In: Web and Internet Economics - 14th International Conference, WINE 2018, Oxford, UK, 15–17 December 2018, Proceedings, pp. 423–437 (2018)
Vetta, A.: Nash equilibria in competitive societies, with applications to facility location, traffic routing and auctions. In: FOCS (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Georgoulaki, E., Kollias, K. (2023). Arbitrary Profit Sharing in Federated Learning Utility Games. In: Deligkas, A., Filos-Ratsikas, A. (eds) Algorithmic Game Theory. SAGT 2023. Lecture Notes in Computer Science, vol 14238. Springer, Cham. https://doi.org/10.1007/978-3-031-43254-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-43254-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43253-8
Online ISBN: 978-3-031-43254-5
eBook Packages: Computer ScienceComputer Science (R0)