Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms that promote novelty and diversity. In practice, the strength of such interventions is typically controlled using global hyperparameters, fixed regularization weights, heuristic caps, or offline tuning strategies. These approaches implicitly assume that a single level of exploration is appropriate across users, contexts, and stages of interaction. In this work, we study exploration saturation as a user-dependent phenomenon arising from fairness- and novelty-driven recommendation strategies. We define exploration saturation as the point at which further increases in exploration no longer improve user utility and may instead reduce engagement or perceived relevance. Rather than proposing a new fairness-aware algorithm or optimizing a specific objective, we empirically analyze how increasing exploration affects users across varied recommendation models. Through longitudinal experiments using MovieLens-1M and Last.fm datasets, our results indicate that fairness-induced exploration exhibits diminishing or non-monotonic returns and varies substantially across users. In particular, users with limited interaction histories tend to reach saturation earlier, suggesting that uniform fairness or novelty pressure can disproportionately disadvantage certain users. These findings reveal a trade-off between fairness and user experience, suggesting that recommendation systems should adapt not only to relevance but also to the amount of fairness-driven exploration applied to individual users.
Figures & tables
Dataset
Users
Items
Interactions
Domain
MovieLens-1M
6,040
3,706
1,000,209
Movies
Last.fm
1,000
17,632
19,150,868
Music
Table 1. Summary statistics of the datasets used in the experiments.
Figure 1. Utility vs. exploration on Last.fm across recommendation models.
Figure 2. Utility vs. exploration on MovieLens-1M across recommendation models.
Figure 3. Utility vs. semantic exploration for NCF.
Figure 4. Utility vs. exploration for MostPopular on MovieLens-1M.
Figure 5. Utility vs. exploration for LightGCN.
Figure 6. Semantic exploration effects for BPR-MF on MovieLens-1M.
Figure 7. Marginal effect of exploration on utility across recommendation models on Last.fm.
Figure 8. Marginal effect of exploration on utility across recommendation models on MovieLens-1M.
Figure 9. Distribution of user-level exploration saturation regimes on MovieLens-1M, stratified by interaction history length. Visualization of user-level exploration saturation regimes on MovieLens-1M.
Figure 10. User-level exploration saturation for NCF on Last.fm.
One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. Models optimized for this definition are typically evaluated on how well demographic attributes can be classified given model representations, with the (implicit) assumption that this measure accurately reflects recommendation parity, i.e., how similar recommendations given to different users are. We challenge this assumption by comparing the amount of demographic information encoded in representations with various measures of how the recommendations differ. We propose two new approaches for measuring how well demographic information can be classified given ranked recommendations. Our results from extensive testing of multiple models on one real and multiple synthetically generated datasets indicate that optimizing for fair representations positively affects recommendation parity, but also that evaluation at the representation level is not a good proxy for measuring this effect when comparing models. We also provide extensive insight into how recommendation-level fairness metrics behave for various models by evaluating their performances on numerous generated datasets with different properties.
Bjørnar Vassøy, Benjamin Kille, Helge Langseth
Norwegian University of Science and Technology, Trondheim, Norway
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.
Centre of Machine Intelligence & Data Science Indian Institute of Technology, Bombay Mumbai, Maharashtra, India · Electrical & Computer Engineering Dept. Georgia Institute of Technology Atlanta, GA, USA · Dept. of Computer Science & Engineering Indian Institute of Technology, Bombay Mumbai, Maharashtra, India +3
Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairness-aware methods often suffer from a fundamental oversight: they assume the observed user state is a faithful representation of true preferences. In reality, implicit feedback is contaminated by popularity-driven noise and exposure bias, creating a distorted state that misleads the RL agent. We argue that the persistent conflict between accuracy and fairness is not merely a reward-shaping issue, but a state estimation failure. In this work, we propose DSRM-HRL, a framework that reformulates fairness-aware recommendation as a latent state purification problem followed by decoupled hierarchical decision-making. We introduce a Denoising State Representation Module (DSRM) based on diffusion models to recover the low-entropy latent preference manifold from high-entropy, noisy interaction histories. Built upon this purified state, a Hierarchical Reinforcement Learning (HRL) agent is employed to decouple conflicting objectives: a high-level policy regulates long-term fairness trajectories, while a low-level policy optimizes short-term engagement under these dynamic constraints. Extensive experiments on high-fidelity simulators (KuaiRec, KuaiRand) demonstrate that DSRM-HRL effectively breaks the "rich-get-richer" feedback loop, achieving a superior Pareto frontier between recommendation utility and exposure equity.
Yun Lu, Xiaoyu Shi, Hong Xie +2
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences Chongqing School, University of Chinese Academy of Sciences Chongqing, China · The First Affiliated Hospital, University of Science and Technology of China Hefei, China · City University of Hong Kong Hong Kong, Hong Kong