# Debiasing Recommendation with Personal Popularity

arXiv: https://arxiv.org/abs/2402.07425 · HTML: https://mlsanity.com/paper/2402.07425/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2024.

## Built on by (most cited first, 7 of 7)

- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [Bridging Semantic Understanding and Popularity Bias with LLMs](https://mlsanity.com/paper/2601.09478/) (2026)
- [Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity](https://mlsanity.com/paper/2505.14310/) (2025)
- [Learning to Alleviate Familiarity Bias in Video Recommendation](https://mlsanity.com/paper/2602.07987/) (2026)
- [Aligning Recommendations with User Popularity Preferences](https://mlsanity.com/paper/2604.01036/) (2026)
- [Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering](https://mlsanity.com/paper/2605.11145/) (2026)
- [The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders](https://mlsanity.com/paper/2606.21911/) (2026)

## Abstract (arXiv)

Global popularity (GP) bias is the phenomenon that popular items are recommended much more frequently than they should be, which goes against the goal of providing personalized recommendations and harms user experience and recommendation accuracy. Many methods have been proposed to reduce GP bias but they fail to notice the fundamental problem of GP, i.e., it considers popularity from a textitglobal perspective of textitall users and uses a single set of popular items, and thus cannot capture the interests of individual users. As such, we propose a user-aware version of item popularity named textitpersonal popularity (PP), which identifies different popular items for each user by considering the users that share similar interests. As PP models the preferences of individual users, it naturally helps to produce personalized recommendations and mitigate GP bias. To integrate PP into recommendation, we design a general textitpersonal popularity aware counterfactual (PPAC) framework, which adapts easily to existing recommendation models. In particular, PPAC recognizes that PP and GP have both direct and indirect effects on recommendations and controls direct effects with counterfactual inference techniques for unbiased recommendations. All codes and datasets are available at urlhttps://github.com/Stevenn9981/PPAC.