Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Platforms for Efficient and Incentive-Aware Collaboration (2402.15169v2)

Published 23 Feb 2024 in cs.GT, cs.DS, and cs.MA

Abstract: Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum et al., 2021]. Implicit in the traditional PoS analysis is the assumption that agents have full knowledge of how their tasks relate to one another. We offer a new perspective on bringing about efficient collaboration among strategic agents using information design. Inspired by the growing importance of collaboration in machine learning (such as platforms for collaborative federated learning and data cooperatives), we propose a framework where the platform has more information about how the agents' tasks relate to each other than the agents themselves. We characterize how and to what degree such platforms can leverage their information advantage to steer strategic agents toward efficient collaboration. Concretely, we consider collaboration networks where each node is a task type held by one agent, and each task benefits from contributions made in their inclusive neighborhood of tasks. This network structure is known to the agents and the platform, but only the platform knows each agent's real location -- from the agents' perspective, their location is determined by a random permutation. We employ private Bayesian persuasion and design two families of persuasive signaling schemes that the platform can use to ensure a small total workload when agents follow the signal. The first family aims to achieve the minmax optimal approximation ratio compared to the optimal collaboration, which is shown to be $\Theta(\sqrt{n})$ for unit-weight graphs, $\Theta(n{2/3})$ for graphs with constant minimum edge weights, and $O(n{3/4})$ for general weighted graphs. The second family ensures per-instance strict improvement compared to full information disclosure.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (65)
  1. A marketplace for data: An algorithmic solution. In Proceedings of the 20th ACM Conference on Economics and Computation (EC), pages 701–726, 2019.
  2. Towards data auctions with externalities. arXiv preprint arXiv:2003.08345, 2020.
  3. AlienVault. Alienvault - open threat exchange. https://en.wikipedia.org/wiki/Open_Threat_Exchange, 2012. Accessed: 2024-02-12.
  4. Persuading voters. American Economic Review, 106(11):3590–3605, 2016.
  5. The price of stability for network design with fair cost allocation. SIAM Journal on Computing, 38(4):1602–1623, 2008.
  6. Private Bayesian persuasion. Journal of Economic Theory, 182:185–217, 2019.
  7. Repeated games with incomplete information. MIT press, 1995.
  8. Open problem: The sample complexity of multi-distribution learning for vc classes. In The Thirty Sixth Annual Conference on Learning Theory (COLT), pages 5943–5949. PMLR, 2023.
  9. Modes of persuasion toward unanimous consent. Theoretical Economics, 13(3):1111–1149, 2018.
  10. Robust predictions in games with incomplete information. Econometrica, 81(4):1251–1308, 2013.
  11. Bayes correlated equilibrium and the comparison of information structures in games. Theoretical Economics, 11(2):487–522, 2016.
  12. Information design: A unified perspective. Journal of Economic Literature, 57(1):44–95, 2019.
  13. Calibrated click-through auctions. In Proceedings of the ACM Web Conference 2022, pages 47–57, 2022.
  14. Genome-wide association studies (GWAS) of schizophrenia: does bigger lead to better results? Current opinion in psychiatry, 25(2):76, 2012.
  15. Hardness results for signaling in Bayesian zero-sum and network routing games. In Proceedings of the 17th ACM Conference on Economics and Computation (EC), pages 479–496, 2016.
  16. Collaborative PAC learning. In Advances in Neural Information Processing Systems (NeurIPS), pages 2389–2398, 2017.
  17. One for one, or all for all: Equilibria and optimality of collaboration in federated learning. In Proceedings of the 38th International Conference on Machine Learning (ICML), pages 1005–1014. PMLR, July 2021a.
  18. Communication-aware collaborative learning. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 35, pages 6786–6793, 2021b.
  19. Simplex partitioning via exponential clocks and the multiway cut problem. In Symposium on Theory of Computing (STOC), pages 535–544, 2013.
  20. Ozan Candogan. Persuasion in networks: Public signals and k-cores. In Proceedings of the 2019 ACM Conference on Economics and Computation, pages 133–134, 2019.
  21. Ozan Candogan. Information design in operations. In Pushing the Boundaries: Frontiers in Impactful OR/OM Research, pages 176–201. INFORMS, 2020.
  22. Optimal signaling of content accuracy: Engagement vs. misinformation.(2017). URL https://ssrn. com/abstract, 3051275, 2017.
  23. Tight bounds for collaborative PAC learning via multiplicative weights. volume 31, 2018.
  24. Bayesian calibrated click-through auction. arXiv preprint arXiv:2306.06554, 2023a.
  25. Mechanism design for collaborative normal mean estimation. arXiv preprint arXiv:2306.06351, 2023b.
  26. Incentivized collaboration in active learning. arXiv preprint arXiv:2311.00260, 2023.
  27. Reducing congestion through information design. In 2017 55th annual allerton conference on communication, control, and computing (allerton), pages 1279–1284. IEEE, 2017.
  28. Model-sharing games: Analyzing federated learning under voluntary participation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 35, pages 5303–5311, 2021a.
  29. Optimality and stability in federated learning: A game-theoretic approach. Advances in Neural Information Processing Systems (NeurIPS), 34:1287–1298, 2021b.
  30. Models of fairness in federated learning. arXiv preprint arXiv:2112.00818, 2021c.
  31. Shaddin Dughmi. Algorithmic information structure design: a survey. ACM SIGecom Exchanges, 15(2):2–24, 2017.
  32. Algorithmic Bayesian persuasion. In Proceedings of the 48th Annual ACM Symposium on Theory of Computing (STOC), pages 412–425, 2016.
  33. Persuasion on networks.(2019). URL https://ssrn. com/abstract, 3375521, 2019.
  34. On-demand sampling: Learning optimally from multiple distributions. In Advances in Neural Information Processing Systems (NeurIPS), volume 35, pages 406–419, 2022.
  35. On the effect of defections in federated learning and how to prevent them. arXiv preprint arXiv:2311.16459, 2023.
  36. Federated learning as a network effects game. arXiv preprint arXiv:2302.08533, 2023.
  37. Evaluating and incentivizing diverse data contributions in collaborative learning. arXiv preprint arXiv:2306.05592, 2023.
  38. Towards efficient data valuation based on the Shapley value. In Artificial Intelligence and Statistics (AISTATS), pages 1167–1176. PMLR, 2019.
  39. Emir Kamenica. Bayesian persuasion and information design. Annual Review of Economics, 11:249–272, 2019.
  40. Bayesian persuasion. American Economic Review, 101(6):2590–2615, 2011.
  41. Mechanisms that incentivize data sharing in federated learning. In Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022), 2022.
  42. Implementing the “wisdom of the crowd”. Journal of Political Economy, 122(5):988–1012, 2014.
  43. Fair yet asymptotically equal collaborative learning. arXiv preprint arXiv:2306.05764, 2023.
  44. Collaborative fairness in federated learning. Federated Learning: Privacy and Incentive, pages 189–204, 2020.
  45. Bayesian incentive-compatible bandit exploration. Operations Research, 68(4):1132–1161, 2020.
  46. Bayesian exploration: Incentivizing exploration in Bayesian games. Operations Research, 70(2):1105–1127, 2022.
  47. Organized information transmission. 2022.
  48. On information design in games. Journal of Political Economy, 128(4):1370–1404, 2020.
  49. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics (AISTATS), pages 1273–1282. PMLR, 2017.
  50. Improved algorithms for collaborative PAC learning. volume 31, 2018.
  51. Crowdsourcing exploration. Management Science, 64(4):1727–1746, 2018.
  52. Binghui Peng. The sample complexity of multi-distribution learning. arXiv preprint arXiv:2312.04027, 2023.
  53. Aviad Rubinstein. Honest signaling in zero-sum games is hard, and lying is even harder. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2017.
  54. Keith E Schnakenberg. Expert advice to a voting body. Journal of Economic Theory, 160:102–113, 2015.
  55. Alma Steingart. A group theory of group theory: Collaborative mathematics and the ‘uninvention’ of a 1000-page proof. Social Studies of Science, 42(2):185–213, 2012.
  56. Ina Taneva. Information design. American Economic Journal: Microeconomics, 11(4):151–185, 2019.
  57. Incentive mechanisms for federated learning: From economic and game theoretic perspective. IEEE transactions on cognitive communications and networking, 8(3):1566–1593, 2022.
  58. Yun Wang. Bayesian persuasion with multiple receivers. Available at SSRN 2625399, 2013.
  59. Incentivized communication for federated bandits. In Advances in Neural Information Processing Systems (NeurIPS), 2023.
  60. The design of approximation algorithms. Cambridge university press, 2011.
  61. Information design for regulating traffic flows under uncertain network state. In 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pages 671–678. IEEE, 2019.
  62. Gradient driven rewards to guarantee fairness in collaborative machine learning. Advances in Neural Information Processing Systems (NeurIPS), 34:16104–16117, 2021.
  63. FAIR: Fair collaborative active learning with individual rationality for scientific discovery. In Artificial Intelligence and Statistics (AISTATS), pages 4033–4057. PMLR, 2023.
  64. A survey of incentive mechanism design for federated learning. IEEE Transactions on Emerging Topics in Computing, 10(2):1035–1044, 2021.
  65. Optimal multi-distribution learning. arXiv preprint arXiv:2312.05134, 2023.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now