# Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective

arXiv: https://arxiv.org/abs/2211.01154 · HTML: https://mlsanity.com/paper/2211.01154/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2022.

## Built on by (most cited first, 11 of 11)

- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Test Time Embedding Normalization for Popularity Bias Mitigation](https://mlsanity.com/paper/2308.11288/) (2023)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling](https://mlsanity.com/paper/2406.10425/) (2024)
- [Graph Relation Aware Continual Learning](https://mlsanity.com/paper/2308.08259/) (2023)
- [T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Data](https://mlsanity.com/paper/2309.02610/) (2023)
- [Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders](https://mlsanity.com/paper/2605.16825/) (2026)
- [Interpretable Imitation Learning with Dynamic Causal Relations](https://mlsanity.com/paper/2310.00489/) (2023)
- [PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems](https://mlsanity.com/paper/2507.19067/) (2025)
- [Aligning Recommendations with User Popularity Preferences](https://mlsanity.com/paper/2604.01036/) (2026)

## Abstract (arXiv)

Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-tailed distribution. Such long-tailed data lead to popularity bias to recommend popular but not personalized items to users. We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items. To address these issues, we propose a simple yet efficient framework to mitigate popularity bias from a gradient perspective. Specifically, we first normalize each user embedding and record accumulated gradients of users and items via popularity bias measures in model training. To address the popularity bias issues, we develop a gradient-based embedding adjustment approach used in model testing. This strategy is generic, model-agnostic, and can be seamlessly integrated into most existing recommender systems. Our extensive experiments on two classic recommendation models and four real-world datasets demonstrate the effectiveness of our method over state-of-the-art debiasing baselines.