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

• URL: http://arxiv.org/abs/2604.08643v1
• Date: Thu, 09 Apr 2026 17:45:15 GMT
• Title: Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
• Abstract summary: We analyze collaboration as a multi-agent linear bandit problem with a transferable utility (TU) cooperative game formulation.<n>We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions.<n>We propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core.
• Score: 18.15244869689104
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Parametric Open Source Games [78.29352305480285]
  We introduce parametric open-source games, a continuous analogue of program equilibria.<n>We derive an exact coupling threshold at which selfish gradient ascent in symmetric $2times2$ games switches from defection toward cooperation.<n>We extend the framework to a neural semantics class whose first-order cooperation condition is governed by the ratio of cross-player to self-player sensitivity.
  arXiv  Detail & Related papers  (2026-06-25T14:14:24Z)
• Breaking $\ extit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values [0.3823356975862005]
  We propose a new framework for meritocratic fairness in budgeted multi-armed bandits with full-bandit feedback.<n>We first extend the Shapley value, a classical solution concept from cooperative game theory, to the $K$-Shapley value.<n>We propose K-SVFair-FBF, a fairness-aware algorithm that adaptively estimates $K$-Shapley value with unknown valuation function.
  arXiv  Detail & Related papers  (2026-05-01T16:20:43Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation [0.9231476323484774]
  This paper introduces KNEXA-FL, a novel framework for orchestrated decentralization.<n>It employs a non-aggregating Central Profiler/Matchmaker that formulates P2P collaboration as a contextual bandit problem.<n>Our experiments show that KNEXA-FL yields substantial gains, improving Pass@1 by approx. 50% relative to random P2P collaboration.
  arXiv  Detail & Related papers  (2026-01-23T19:18:43Z)
• A Ratio-Based Shapley Value for Collaborative Machine Learning - Extended Version [1.7778609937758325]
  Collaborative machine learning enables multiple data owners to jointly train models for improved predictive performance.<n> Ensuring incentive compatibility and fair contribution-based rewards remains a critical challenge.<n>We introduce a ratio-based Shapley value that replaces the standard additive formulation with a relative contribution measure.
  arXiv  Detail & Related papers  (2025-10-15T08:08:18Z)
• Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork [25.31548780542065]
  We aim to investigate a recently proposed problem for open multi-agent systems, referred as n-agent ad hoc teamwork (NAHT)<n>Existing methods tend to be based on design and consequently lack theoretical rigor and ambiguous credit assignment among agents.<n>To address these limitations, we model and solve NAHT through the lens of cooperative game theory.
  arXiv  Detail & Related papers  (2025-06-12T20:44:09Z)
• Shapley Value Approximation Based on k-Additive Games [21.023521613326654]
  The Shapley value is the prevalent solution for fair division problems in which a payout is to be divided among multiple agents.<n>Despite its popularity and axiomatic justification, the Shapley value suffers from a computational complexity that scales exponentially with the number of entities involved.<n>We propose SVA$k_textADD$, a novel approximation method that fits a $k$-additive surrogate game.
  arXiv  Detail & Related papers  (2025-02-07T08:52:57Z)
• Self-Localized Collaborative Perception [49.86110931859302]
  We propose$mathttCoBEVGlue$, a novel self-localized collaborative perception system. $mathttCoBEVGlue$ is a novel spatial alignment module, which provides the relative poses between agents. $mathttCoBEVGlue$ achieves state-of-the-art detection performance under arbitrary localization noises and attacks.
  arXiv  Detail & Related papers  (2024-06-18T15:26:54Z)
• PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators [30.02006609876506]
  We present the Proportional Payoff Allocation Game ( PPA-Game), which characterizes situations where agents compete for divisible resources.<n>Such dynamics simulate content creators on online recommender systems like YouTube and TikTok, who compete for finite consumer attention.<n>We propose an online algorithm facilitating each agent's cumulative payoffs over $T$ rounds.
  arXiv  Detail & Related papers  (2024-03-22T14:13:11Z)
• Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property [89.96815099996132]
  We develop a new framework to characterize optimistic policy gradient methods in multi-player games with a single controller. Our approach relies on a natural generalization of the classical Minty property that we introduce, which we anticipate to have further applications beyond Markov games.
  arXiv  Detail & Related papers  (2023-12-19T11:34:10Z)
• Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents [52.75161794035767]
  We introduce a class of bandit algorithms that meet the two objectives of performance incentivization and robustness simultaneously.<n>We show that settings where the principal has no information about the arms' performance characteristics can be handled by combining ideas from second price auctions with our algorithms.
  arXiv  Detail & Related papers  (2023-12-13T06:54:49Z)
• A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning [53.83345471268163]
  We investigate learning the equilibria in non-stationary multi-agent systems. We show how to test for various types of equilibria by a black-box reduction to single-agent learning.
  arXiv  Detail & Related papers  (2023-06-12T23:48:24Z)
• Modeling Content Creator Incentives on Algorithm-Curated Platforms [76.53541575455978]
  We study how algorithmic choices affect the existence and character of (Nash) equilibria in exposure games. We propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
  arXiv  Detail & Related papers  (2022-06-27T08:16:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.