Stay or Stray - A Dynamical Systems Viewpoint of Popularity Bias

arXiv:2608.10474v1 Announce Type: cross Abstract: Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increasingly favour it while degrading recommendation quality for niche users. While extensive empirical evidence of popularity bias exists, the dynamics leading to its emergence are not well understood. In this work, we study the coupled evolution of recommender model updates and user engagement through the lens of dynamical systems. We formulate a stochastic process and analyse its asymptotic behaviour through an ordinary differential equation (ODE) framework grounded in two-time-scale stochastic approximation. We characterise the equilibrium points of this dynamical system, and derive conditions under which popularity bias is provably emergent, as well as conditions under which symmetric retention of all user classes is possible. We conduct experiments on synthetic data and real-world production logs derived from a large-scale commercial music recommendation platform to validate our theoretical results.

Related

• Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
• The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders
• VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation

Source: arXiv cs.LG | 2026-08-12