# Causal Intervention for Leveraging Popularity Bias in Recommendation

arXiv: https://arxiv.org/abs/2105.06067 · HTML: https://mlsanity.com/paper/2105.06067/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2021.

## Built on by (most cited first, 30 of 116)

- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion](https://mlsanity.com/paper/2110.10926/) (2021)
- [Self-Supervised Hypergraph Transformer for Recommender Systems](https://mlsanity.com/paper/2207.14338/) (2022)
- [MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation](https://mlsanity.com/paper/2308.11175/) (2023)
- [Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative](https://mlsanity.com/paper/2210.03801/) (2022)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random](https://mlsanity.com/paper/2205.04701/) (2022)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [A Causal View of Entity Bias in (Large) Language Models](https://mlsanity.com/paper/2305.14695/) (2023)
- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization](https://mlsanity.com/paper/2206.01022/) (2022)
- [Stealthy Attack on Large Language Model based Recommendation](https://mlsanity.com/paper/2402.14836/) (2024)
- [TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations](https://mlsanity.com/paper/2203.10258/) (2022)
- [Comprehensive Fair Meta-learned Recommender System](https://mlsanity.com/paper/2206.04789/) (2022)
- [Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations](https://mlsanity.com/paper/2304.09085/) (2023)
- [Causal Incremental Graph Convolution for Recommender System Retraining](https://mlsanity.com/paper/2108.06889/) (2021)
- [Deconfounded Causal Collaborative Filtering](https://mlsanity.com/paper/2110.07122/) (2021)
- [A Survey on Fairness-aware Recommender Systems](https://mlsanity.com/paper/2306.00403/) (2023)
- [Causal Disentanglement for Semantics-Aware Intent Learning in Recommendation](https://mlsanity.com/paper/2202.02576/) (2022)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Unbiased Knowledge Distillation for Recommendation](https://mlsanity.com/paper/2211.14729/) (2022)
- [Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobao](https://mlsanity.com/paper/2306.03527/) (2023)
- [TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems](https://mlsanity.com/paper/2308.14355/) (2023)
- [Recommendation Fairness: From Static to Dynamic](https://mlsanity.com/paper/2109.03150/) (2021)
- [The Unfairness of Active Users and Popularity Bias in Point-of-Interest Recommendation](https://mlsanity.com/paper/2202.13307/) (2022)
- [Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias](https://mlsanity.com/paper/2405.20718/) (2024)
- [Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies](https://mlsanity.com/paper/2502.00690/) (2025)

## Abstract (arXiv)

Recommender system usually faces popularity bias issues: from the data perspective, items exhibit uneven (long-tail) distribution on the interaction frequency; from the method perspective, collaborative filtering methods are prone to amplify the bias by over-recommending popular items. It is undoubtedly critical to consider popularity bias in recommender systems, and existing work mainly eliminates the bias effect. However, we argue that not all biases in the data are bad -- some items demonstrate higher popularity because of their better intrinsic quality. Blindly pursuing unbiased learning may remove the beneficial patterns in the data, degrading the recommendation accuracy and user satisfaction. This work studies an unexplored problem in recommendation -- how to leverage popularity bias to improve the recommendation accuracy. The key lies in two aspects: how to remove the bad impact of popularity bias during training, and how to inject the desired popularity bias in the inference stage that generates top-K recommendations. This questions the causal mechanism of the recommendation generation process. Along this line, we find that item popularity plays the role of confounder between the exposed items and the observed interactions, causing the bad effect of bias amplification. To achieve our goal, we propose a new training and inference paradigm for recommendation named Popularity-bias Deconfounding and Adjusting (PDA). It removes the confounding popularity bias in model training and adjusts the recommendation score with desired popularity bias via causal intervention. We demonstrate the new paradigm on latent factor model and perform extensive experiments on three real-world datasets. Empirical studies validate that the deconfounded training is helpful to discover user real interests and the inference adjustment with popularity bias could further improve the recommendation accuracy.