# Invariant Collaborative Filtering to Popularity Distribution Shift

arXiv: https://arxiv.org/abs/2302.05328 · HTML: https://mlsanity.com/paper/2302.05328/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2023.

## Built on by (most cited first, 23 of 23)

- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion](https://mlsanity.com/paper/2310.20453/) (2023)
- [Towards 3D Molecule-Text Interpretation in Language Models](https://mlsanity.com/paper/2401.13923/) (2024)
- [How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective](https://mlsanity.com/paper/2404.12008/) (2024)
- [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)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2408.00490/) (2024)
- [Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias](https://mlsanity.com/paper/2405.20718/) (2024)
- [PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation](https://mlsanity.com/paper/2411.00163/) (2024)
- [Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion Model](https://mlsanity.com/paper/2501.15555/) (2025)
- [Generalized Incremental Learning under Concept Drift across Evolving Data Streams](https://mlsanity.com/paper/2506.05736/) (2025)
- [ORCDF: An Oversmoothing-Resistant Cognitive Diagnosis Framework for Student Learning in Online Education Systems](https://mlsanity.com/paper/2407.17476/) (2024)
- [D-Tracker: Modeling Interest Diffusion in Social Activity Tensor Data Streams](https://mlsanity.com/paper/2505.00242/) (2025)
- [Can We Understand Plasticity Through Neural Collapse?](https://mlsanity.com/paper/2404.02719/) (2024)
- [Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations](https://mlsanity.com/paper/2501.04762/) (2025)
- [Advancing Loss Functions in Recommender Systems: A Comparative Study with a R'enyi Divergence-Based Solution](https://mlsanity.com/paper/2506.15120/) (2025)
- [Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity](https://mlsanity.com/paper/2505.14310/) (2025)
- [BPL: Bias-adaptive Preference Distillation Learning for Recommender System](https://mlsanity.com/paper/2510.16076/) (2025)
- [CIRR: Causal-Invariant Retrieval-Augmented Recommendation with Faithful Explanations under Distribution Shift](https://mlsanity.com/paper/2512.18683/) (2025)
- [The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders](https://mlsanity.com/paper/2606.21911/) (2026)
- [Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2608.03647/) (2026)
- [GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2609.02162/) (2026)

## Abstract (arXiv)

Collaborative Filtering (CF) models, despite their great success, suffer from severe performance drops due to popularity distribution shifts, where these changes are ubiquitous and inevitable in real-world scenarios. Unfortunately, most leading popularity debiasing strategies, rather than tackling the vulnerability of CF models to varying popularity distributions, require prior knowledge of the test distribution to identify the degree of bias and further learn the popularity-entangled representations to mitigate the bias. Consequently, these models result in significant performance benefits in the target test set, while dramatically deviating the recommendation from users' true interests without knowing the popularity distribution in advance. In this work, we propose a novel learning framework, Invariant Collaborative Filtering (InvCF), to discover disentangled representations that faithfully reveal the latent preference and popularity semantics without making any assumption about the popularity distribution. At its core is the distillation of unbiased preference representations (i.e., user preference on item property), which are invariant to the change of popularity semantics, while filtering out the popularity feature that is unstable or outdated. Extensive experiments on five benchmark datasets and four evaluation settings (i.e., synthetic long-tail, unbiased, temporal split, and out-of-distribution evaluations) demonstrate that InvCF outperforms the state-of-the-art baselines in terms of popularity generalization ability on real recommendations. Visualization studies shed light on the advantages of InvCF for disentangled representation learning. Our codes are available at https://github.com/anzhang314/InvCF.