Understanding Partnership Formation and Repeated Contributions in Federated Learning: An Analytical Investigation

References

• Akin E (2016) The iterated prisoner’s dilemma: Good strategies and their dynamics. Assani I, ed. Ergodic Theory, Advances in Dynamical Systems (De Gruyter, Berlin), 77–107.Google Scholar
• Aledhari M, Razzak R, Parizi RM, Saeed F (2020) Federated learning: A survey on enabling technologies, protocols, and applications. IEEE Access 8:140699–140725.Crossref, Google Scholar
• Arend RJ, Seale DA (2005) Modeling alliance activity: An iterated prisoners’ dilemma with exit option. Strategic Management J. 26(11):1057–1074.Crossref, Google Scholar
• Aumann RJ (2006) War and peace. Proc. National Acad. Sci. USA 103(46):17075–17078.Crossref, Google Scholar
• Axelrod R, Hamilton WD (1981) The evolution of cooperation. Science 211(4489):1390–1396.Crossref, Google Scholar
• Bagdasaryan E, Veit A, Hua Y, Estrin D, Shmatikov V (2020) How to backdoor federated learning. Chiappa S, Calandra R, eds. Proc. Internat. Conf. on Artificial Intelligence and Statist., 2938–2948. https://aistats.org/aistats2020/.Google Scholar
• Bai G, Jiang JX, Flasher R (2017) Hospital risk of data breaches. JAMA Internal Medicine 177(6):878–880.Crossref, Google Scholar
• Bhowmick A, Duchi J, Freudiger J, Kapoor G, Rogers R (2018) Protection against reconstruction and its applications in private federated learning. Preprint, submitted December 3, https://arxiv.org/abs/1812.00984.Google Scholar
• Blanchard P, El Mhamdi EM, Guerraoui R, Stainer J (2017) Machine learning with adversaries: Byzantine tolerant gradient descent. von Luxburg U, Guyon I, Bengio S, Wallach H, Fergus R, eds. Proc. 31st Internat. Conf. on Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 118–128.Google Scholar
• Blum A, Haghtalab N, Phillips RL, Shao H (2021) One for one, or all for all: Equilibria and optimality of collaboration in federated learning. Meila M, Zhang T, eds. Proc. 38th Internat. Conf. Machine Learn. (ICML), vol. 139 (PMLR, New York), 1005–1014.Google Scholar
• Chen X, Liu C, Li B, Lu K, Song D (2017) Targeted backdoor attacks on deep learning systems using data poisoning. Preprint, submitted December 15, https://arxiv.org/abs/1712.05526.Google Scholar
• Chong SY, Yao X (2006) Self-adapting payoff matrices in repeated interactions. Louis SJ, Kendall G, eds. Proc. IEEE Sympos. on Comput. Intelligence and Games (IEEE, Piscataway, NJ), 103–110.Google Scholar
• Damaskinos G, Guerraoui R, Patra R, Taziki M, et al.. (2018) Asynchronous byzantine machine learning (the case of SGD). Dy JG, Krause A, eds. Proc. 35th Internat. Conf. Machine Learn. (ICML), vol. 80 (PMLR, New York), 1145–1154.Google Scholar
• Dayan I, Roth HR, Zhong A, Harouni A, Gentili A, Abidin AZ, Liu A, et al. (2021) Federated learning for predicting clinical outcomes in patients with covid-19. Nature Medicine 27(10):1735–1743.Crossref, Google Scholar
• Donahue K, Kleinberg J (2021a) Model-sharing games: Analyzing federated learning under voluntary participation. 35th AAAI Conf. Artificial Intelligence, 33rd Conf. Innovative Appl. Artificial Intelligence (IAAI), 11th Sympos. Ed. Adv. Artificial Intelligence (EAAI), vol. 35 (AAAI Press, Washington, DC), 5303–5311.Google Scholar
• Donahue K, Kleinberg J (2021b) Optimality and stability in federated learning: A game-theoretic approach. Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, eds. Adv. Neural Inform. Processing Systems, vol. 34 (Curran Associates, Inc., Red Hook, New York), 1287–1298.Google Scholar
• Geiping J, Bauermeister H, Dröge H, Moeller M (2020) Inverting gradients: How easy is it to break privacy in federated learning? Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Adv. Neural Inform. Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 16937–16947.Google Scholar
• Geyer RC, Klein T, Nabi M (2017) Differentially private federated learning: A client level perspective. Preprint, submitted December 20, https://arxiv.org/abs/1712.07557.Google Scholar
• Guerraoui R, Mhamdi EME, Guerraoui R, Rouault S (2018) The hidden vulnerability of distributed learning in byzantium. Dy JG, Krause A, eds. Proc. 35th Internat. Conf. on Machine Learn. (PMLR, New York), 3521–3530.Google Scholar
• Han T, Nebelung S, Haarburger C, Horst N, Reinartz S, Merhof D, Kiessling F, et al. (2020) Breaking medical data sharing boundaries by using synthesized radiographs. Sci. Adv. 6(49):eabb7973.Crossref, Google Scholar
• Hard A, Rao K, Mathews R, Ramaswamy S, Beaufays F, Augenstein S, Eichner H, et al. (2018) Federated learning for mobile keyboard prediction. Preprint, submitted November 8, https://arxiv.org/abs/1811.03604.Google Scholar
• Hegiste V, Legler T, Ruskowski M (2022) Application of federated machine learning in manufacturing. Proc. Internat. Conf. on Industry 4.0 Tech (IEEE, Piscataway, NJ), 1–8.Google Scholar
• Hilbe C, Nowak MA, Sigmund K (2013) Evolution of extortion in iterated prisoner’s dilemma games. Proc. National Acad. Sci. USA 110(17):6913–6918.Crossref, Google Scholar
• Jurišić M, Kermek D, Konecki M (2012) A review of iterated prisoner’s dilemma strategies. Proc. 35th Internat. Convention MIPRO (IEEE, Piscataway, NJ), 1093–1097.Google Scholar
• Kairouz P, McMahan HB, Avent B, Bellet A, Bennis M, Bhagoji AN, Bonawitz K, et al. (2019) Advances and open problems in federated learning. Preprint, submitted December 10, https://arxiv.org/abs/1912.04977.Google Scholar
• Kaissis G, Ziller A, Passerat-Palmbach J, Ryffel T, Usynin D, Trask A, Lima I, et al. (2021) End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nature Machine Intelligence 3(6):473–484.Crossref, Google Scholar
• Kaissis GA, Makowski MR, Rückert D, Braren RF (2020) Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence 2(6):305–311.Crossref, Google Scholar
• Kendall G, Yao X, Chong SY (2007) The Iterated Prisoners’ Dilemma: 20 Years on, vol. 4 (World Scientific, Singapore).Crossref, Google Scholar
• Lecuyer M, Atlidakis V, Geambasu R, Hsu D, Jana S (2019) Certified robustness to adversarial examples with differential privacy. Proc. IEEE Sympos. on Security and Privacy (IEEE, Piscataway, NJ), 656–672.Google Scholar
• Li T, Sahu AK, Talwalkar A, Smith V (2020) Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine 37(3):50–60.Crossref, Google Scholar
• Li W, Milletarì F, Xu D, Rieke N, Hancox J, Zhu W, Baust M, et al. (2019) Privacy-preserving federated brain tumour segmentation. Proc. Internat. Workshop on Machine Learn. in Medical Imaging (Springer, Berlin), 133–141.Google Scholar
• Liu Y, Xie Y, Srivastava A (2017) Neural trojans. Proc. IEEE Internat. Conf. on Computer Design (IEEE, Piscataway, NJ), 45–48.Google Scholar
• McCoy K (2017) Target to pay $18.5m for 2013 data breach that affected 41 million consumers. Accessed July 27, 2023, https://www.usatoday.com/story/money/2017/05/23/target-pay-185m-2013-data-breach-affected-consumers/102063932.Google Scholar
• McCoy TH, Perlis RH (2018) Temporal trends and characteristics of reportable health data breaches, 2010–2017. JAMA 320(12):1282–1284.Crossref, Google Scholar
• McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. Singh A, Zhu J, eds. Artificial Intelligence and Statistics (PMLR, New York), 1273–1282.Google Scholar
• Melloddy (2019) Machine learning ledger orchestration for drug discovery. Accessed July 27, 2023, https://www.melloddy.eu/.Google Scholar
• Miller AR, Tucker C (2009) Privacy protection and technology diffusion: The case of electronic medical records. Management Sci. 55(7):1077–1093.Link, Google Scholar
• Miller AR, Tucker C (2014) Health information exchange, system size and information silos. J. Health Econom. 33:28–42.Crossref, Google Scholar
• Musketeer (2019) Machine learning to augment shared knowledge in federated privacy-preserving scenarios. Accessed July 27, 2023, https://musketeer.eu/.Google Scholar
• Press WH, Dyson FJ (2012) Iterated prisoner’s dilemma contains strategies that dominate any evolutionary opponent. Proc. National Acad. Sci. USA 109(26):10409–10413.Crossref, Google Scholar
• Rezaei G, Kirley M (2009) The effects of time-varying rewards on the evolution of cooperation. Evolution Intelligence 2(4):207–218.Crossref, Google Scholar
• Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, Bakas S, et al. (2020) The future of digital health with federated learning. NPJ Digital Medicine 3(1):1–7.Crossref, Google Scholar
• Roth HR, Chang K, Singh P, Neumark N, Li W, Gupta V, Gupta S, et al. (2020) Federated learning for breast density classification: A real-world implementation. Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning (Springer, Berlin), 181–191.Crossref, Google Scholar
• Sarma KV, Harmon S, Sanford T, Roth HR, Xu Z, Tetreault J, Xu D, et al. (2021) Federated learning improves site performance in multicenter deep learning without data sharing. J. Amer. Medical Inform. Assoc. 28(6):1259–1264.Crossref, Google Scholar
• Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, et al. (2020) Federated learning in medicine: Facilitating multi-institutional collaborations without sharing patient data. Sci. Rep. 10(1):1–12.Crossref, Google Scholar
• Tang M, Wong VW (2021) An incentive mechanism for cross-silo federated learning: A public goods perspective. Proc. IEEE INFOCOM Confe. on Computer Comm. (IEEE, Piscataway, NJ), 1–10.Google Scholar
• Tomochi M, Kono M (2002) Spatial prisoner’s dilemma games with dynamic payoff matrices. Phys. Rev. E 65(2):026112.Crossref, Google Scholar
• Tran B, Li J, Madry A (2018) Spectral signatures in backdoor attacks. Preprint, submitted November 1, https://arxiv.org/abs/1811.00636.Google Scholar
• Tu X, Zhu K, Luong NC, Niyato D, Zhang Y, Li J (2022) Incentive mechanisms for federated learning: From economic and game theoretic perspective. IEEE Trans. Cognitive Comm. Networks 8(3):1566–1593.Crossref, Google Scholar
• Wang H, Sreenivasan K, Rajput S, Vishwakarma H, Agarwal S, Sohn J, Lee K, et al. (2020a) Attack of the tails: Yes, you really can backdoor federated learning. Preprint, submitted July 9, https://arxiv.org/abs/2007.05084.Google Scholar
• Wang P, Shen C, Roth HR, Yang D, Xu D, Oda M, Misawa K, et al. (2020b) Automated pancreas segmentation using multi-institutional collaborative deep learning. Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning (Springer, Berlin), 192–200.Crossref, Google Scholar
• Webank (2019) WeBank and Swiss resigned cooperation MOU. Accessed July 27, 2023, https://markets.businessinsider.com/news/stocks/webank-and-swiss-re-signed-cooperation-mou-1028228738.Google Scholar
• Wedekind C, Milinski M (1996) Human cooperation in the simultaneous and the alternating prisoner’s dilemma: Pavlov vs. generous tit-for-tat. Proc. National Acad. Sci. USA 93(7):2686–2689.Crossref, Google Scholar
• Winder D (2020) Google chrome privacy lawsuit: Could you get a $5,000 payout? Accessed July 27, 2023, https://www.forbes.com/sites/daveywinder/2020/06/03/google-chrome-privacy-lawsuit-could-you-get-a-5000-payout-incognito-mode-class-action/?sh=596e26d51485.Google Scholar
• Wu B, Zhao S, Sun G, Zhang X, Su Z, Zeng C, Liu Z (2019) P3SGD: Patient privacy preserving SGD for regularizing deep CNNs in pathological image classification. Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ), 2099–2108.Google Scholar
• Xie C, Koyejo O, Gupta I (2018) Generalized Byzantine-tolerant SGD. Preprint, submitted March 23, https://arxiv.org/abs/1802.10116.Google Scholar
• Xu J, Glicksberg BS, Su C, Walker P, Bian J, Wang F (2020) Federated learning for healthcare informatics. J. Healthcare Inform. Res. 5:1–19. https://doi.org/10.1007/s41666-020-00082-4.Crossref, Google Scholar
• Yang Q, Fan L, Tong R, Lv A (2021) IEEE federated machine learning. IEEE Federated Machine Learning - White Paper, 1–18.Google Scholar
• Yang Q, Liu Y, Cheng Y, Kang Y, Chen T, Yu H (2019) Federated learning. Synthetic Lectures Artificial Intelligence Machine Learn. 13(3):1–207.Crossref, Google Scholar
• Yin D, Chen Y, Kannan R, Bartlett P (2018) Byzantine-robust distributed learning: Toward optimal statistical rates. Dy JG, Krause A, eds. Proc. 35th Internat. Conf. Machine Learn. (ICML), vol. 80 (PMLR, New York), 5650–5659.Google Scholar
• Yu H, Liu Z, Liu Y, Chen T, Cong M, Weng X, Niyato D, et al. (2020) A sustainable incentive scheme for federated learning. IEEE Intelligent Systems 35(4):58–69.Crossref, Google Scholar
• Zhang N, Ma Q, Chen X (2022) Enabling long-term cooperation in cross-silo federated learning: A repeated game perspective. IEEE Trans. Mobile Comput. 22(7):3910–3924.Crossref, Google Scholar
• Zhu L, Han S (2020) Deep leakage from gradients. Federated Learning (Springer, Berlin), 17–31.Crossref, Google Scholar