Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

Ramakrishnan K, Arpit Agarwal, Lakshmi Subramanian, Maximilian Nickel
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:2404-2412, 2026.

Abstract

User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator’s content influences the system’s learning and, in turn, the exposure of other creators’ contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition’s value equals the negative sum of its members’ cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with—and diverges from—the Shapley fairness across different settings and algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-k26a, title = { Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits }, author = {K, Ramakrishnan and Agarwal, Arpit and Subramanian, Lakshmi and Nickel, Maximilian}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {2404--2412}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/k26a/k26a.pdf}, url = {https://proceedings.mlr.press/v300/k26a.html}, abstract = { User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator’s content influences the system’s learning and, in turn, the exposure of other creators’ contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition’s value equals the negative sum of its members’ cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with—and diverges from—the Shapley fairness across different settings and algorithms. } }
Endnote
%0 Conference Paper %T Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits %A Ramakrishnan K %A Arpit Agarwal %A Lakshmi Subramanian %A Maximilian Nickel %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-k26a %I PMLR %P 2404--2412 %U https://proceedings.mlr.press/v300/k26a.html %V 300 %X User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator’s content influences the system’s learning and, in turn, the exposure of other creators’ contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition’s value equals the negative sum of its members’ cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with—and diverges from—the Shapley fairness across different settings and algorithms.
APA
K, R., Agarwal, A., Subramanian, L. & Nickel, M.. (2026). Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:2404-2412 Available from https://proceedings.mlr.press/v300/k26a.html.

Related Material