PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators

Abstract

In this paper, we present the Proportional Payoff Allocation Game (PPA-Game), which characterizes situations where agents compete for divisible resources. In the PPA-game, agents select from available resources, and their payoffs are proportionately determined based on heterogeneous weights attributed to them. Such dynamics simulate content creators on online recommender systems like YouTube and TikTok, who compete for finite consumer attention, with content exposure reliant on inherent and distinct quality. We first conduct a game-theoretical analysis of the PPA-Game. While the PPA-Game does not always guarantee the existence of a pure Nash equilibrium (PNE), we identify prevalent scenarios ensuring its existence. Simulated experiments further prove that the cases where PNE does not exist rarely happen. Beyond analyzing static payoffs, we further discuss the agents' online learning about resource payoffs by integrating a multi-player multi-armed bandit framework. We propose an online algorithm facilitating each agent's maximization of cumulative payoffs over $T$ rounds. Theoretically, we establish that the regret of any agent is bounded by $O({\log }^{1+\eta }T)$ for any $\eta >0$. Empirical results further validate the effectiveness of our online learning approach.

KDD 2025

References in corpus (15)

• FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
• Game of Thrones: Fully Distributed Learning for Multi-Player Bandits
• A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers
• Bandit Learning in Decentralized Matching Markets
• Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributions
• Decentralized Multi-player Multi-armed Bandits with No Collision Information
• Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
• Selfish Robustness and Equilibria in Multi-Player Bandits
• Competing Bandits in Matching Markets
• Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
• Multiplayer Bandit Learning, from Competition to Cooperation
• Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information
• Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?
• Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms
• Product Ranking for Revenue Maximization with Multiple Purchases