# Robust Collaborative Filtering to Popularity Distribution Shift

arXiv: https://arxiv.org/abs/2310.10696 · HTML: https://mlsanity.com/paper/2310.10696/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 75 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Neural Collaborative Filtering vs. Matrix Factorization Revisited](https://mlsanity.com/paper/2005.09683/) (2020)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems](https://mlsanity.com/paper/1905.04413/) (2019)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation](https://mlsanity.com/paper/2110.15114/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (2017)
- [Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback](https://mlsanity.com/paper/1909.03601/) (2019)
- [Session-based Social Recommendation via Dynamic Graph Attention Networks](https://mlsanity.com/paper/1902.09362/) (2019)
- [On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law](https://mlsanity.com/paper/2005.09241/) (2020)
- [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion](https://mlsanity.com/paper/1905.01866/) (2019)
- [Deconfounded Recommendation for Alleviating Bias Amplification](https://mlsanity.com/paper/2105.10648/) (2021)
- [A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation](https://mlsanity.com/paper/2010.15982/) (2020)
- [Collaborative Memory Network for Recommendation Systems](https://mlsanity.com/paper/1804.10862/) (2018)
- [ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance](https://mlsanity.com/paper/2005.10545/) (2020)
- [Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering](https://mlsanity.com/paper/2210.11054/) (2022)

## Built on by (most cited first, 12 of 12)

- [Language Representations Can be What Recommenders Need: Findings and Potentials](https://mlsanity.com/paper/2407.05441/) (2024)
- [Dual Test-time Training for Out-of-distribution Recommender System](https://mlsanity.com/paper/2407.15620/) (2024)
- [Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2408.00490/) (2024)
- [Preference Diffusion for Recommendation](https://mlsanity.com/paper/2410.13117/) (2024)
- [Heterophily-Aware Fair Recommendation using Graph Convolutional Networks](https://mlsanity.com/paper/2402.03365/) (2024)
- [Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations](https://mlsanity.com/paper/2501.04762/) (2025)
- [Towards a Theoretical Understanding of Two Tower Recommendation Models](https://mlsanity.com/paper/2403.00802/) (2024)
- [Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity](https://mlsanity.com/paper/2505.14310/) (2025)
- [High Order Collaboration-Oriented Federated Graph Neural Network for Accurate QoS Prediction](https://mlsanity.com/paper/2507.05308/) (2025)
- [PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems](https://mlsanity.com/paper/2507.19067/) (2025)
- [Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System](https://mlsanity.com/paper/2602.16124/) (2026)
- [Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2608.03647/) (2026)

## Abstract (arXiv)

In leading collaborative filtering (CF) models, representations of users and items are prone to learn popularity bias in the training data as shortcuts. The popularity shortcut tricks are good for in-distribution (ID) performance but poorly generalized to out-of-distribution (OOD) data, i.e., when popularity distribution of test data shifts w.r.t. the training one. To close the gap, debiasing strategies try to assess the shortcut degrees and mitigate them from the representations. However, there exist two deficiencies: (1) when measuring the shortcut degrees, most strategies only use statistical metrics on a single aspect (i.e., item frequency on item and user frequency on user aspect), failing to accommodate the compositional degree of a user-item pair; (2) when mitigating shortcuts, many strategies assume that the test distribution is known in advance. This results in low-quality debiased representations. Worse still, these strategies achieve OOD generalizability with a sacrifice on ID performance. In this work, we present a simple yet effective debiasing strategy, PopGo, which quantifies and reduces the interaction-wise popularity shortcut without any assumptions on the test data. It first learns a shortcut model, which yields a shortcut degree of a user-item pair based on their popularity representations. Then, it trains the CF model by adjusting the predictions with the interaction-wise shortcut degrees. By taking both causal- and information-theoretical looks at PopGo, we can justify why it encourages the CF model to capture the critical popularity-agnostic features while leaving the spurious popularity-relevant patterns out. We use PopGo to debias two high-performing CF models (MF, LightGCN) on four benchmark datasets. On both ID and OOD test sets, PopGo achieves significant gains over the state-of-the-art debiasing strategies (e.g., DICE, MACR).