# Causal Collaborative Filtering

arXiv: https://arxiv.org/abs/2102.01868 · HTML: https://mlsanity.com/paper/2102.01868/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 86 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 26 of 26)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [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)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Neural Attentive Session-based Recommendation](https://mlsanity.com/paper/1711.04725/) (2017)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [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)
- [Unbiased Learning to Rank with Unbiased Propensity Estimation](https://mlsanity.com/paper/1804.05938/) (2018)
- [Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation](https://mlsanity.com/paper/1805.03352/) (2018)
- [Neural Logic Reasoning](https://mlsanity.com/paper/2008.09514/) (2020)
- [Neural Collaborative Reasoning](https://mlsanity.com/paper/2005.08129/) (2020)
- [PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems](https://mlsanity.com/paper/1911.08378/) (2019)
- [Security and Privacy on Blockchain](https://mlsanity.com/paper/1903.07602/) (2019)
- [Revisiting Alternative Experimental Settings for Evaluating Top-N Item Recommendation Algorithms](https://mlsanity.com/paper/2010.04484/) (2020)
- [A Re-visit of the Popularity Baseline in Recommender Systems](https://mlsanity.com/paper/2005.13829/) (2020)
- [Unbiased Learning for the Causal Effect of Recommendation](https://mlsanity.com/paper/2008.04563/) (2020)
- [Simpson's paradox in Covid-19 case fatality rates: a mediation analysis of age-related causal effects](https://mlsanity.com/paper/2005.07180/) (2020)
- [Using Simpson's Paradox to Discover Interesting Patterns in Behavioral Data](https://mlsanity.com/paper/1805.03094/) (2018)
- [Can you Trust the Trend: Discovering Simpson's Paradoxes in Social Data](https://mlsanity.com/paper/1801.04385/) (2018)

## Built on by (most cited first, 13 of 13)

- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Deconfounded Causal Collaborative Filtering](https://mlsanity.com/paper/2110.07122/) (2021)
- [AutoLossGen: Automatic Loss Function Generation for Recommender Systems](https://mlsanity.com/paper/2204.13160/) (2022)
- [Recommender systems based on graph embedding techniques: A comprehensive review](https://mlsanity.com/paper/2109.09587/) (2021)
- [Causal Lifting and Link Prediction](https://mlsanity.com/paper/2302.01198/) (2023)
- [Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)](https://mlsanity.com/paper/2208.11083/) (2022)
- [CSRec: Rethinking Sequential Recommendation from A Causal Perspective](https://mlsanity.com/paper/2409.05872/) (2024)
- [Dynamic Causal Collaborative Filtering](https://mlsanity.com/paper/2208.11094/) (2022)
- [Causal Structure Learning with Recommendation System](https://mlsanity.com/paper/2210.10256/) (2022)
- [Deep Causal Reasoning for Recommendations](https://mlsanity.com/paper/2201.02088/) (2022)
- [Causal Discovery and Inference towards Urban Elements and Associated Factors](https://mlsanity.com/paper/2503.06395/) (2025)
- [Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation](https://mlsanity.com/paper/2510.04502/) (2025)

## Abstract (arXiv)

Many of the traditional recommendation algorithms are designed based on the fundamental idea of mining or learning correlative patterns from data to estimate the user-item correlative preference. However, pure correlative learning may lead to Simpson's paradox in predictions, and thus results in sacrificed recommendation performance. Simpson's paradox is a well-known statistical phenomenon, which causes confusions in statistical conclusions and ignoring the paradox may result in inaccurate decisions. Fortunately, causal and counterfactual modeling can help us to think outside of the observational data for user modeling and personalization so as to tackle such issues. In this paper, we propose Causal Collaborative Filtering (CCF) -- a general framework for modeling causality in collaborative filtering and recommendation. We provide a unified causal view of CF and mathematically show that many of the traditional CF algorithms are actually special cases of CCF under simplified causal graphs. We then propose a conditional intervention approach for do-operations so that we can estimate the user-item causal preference based on the observational data. Finally, we further propose a general counterfactual constrained learning framework for estimating the user-item preferences. Experiments are conducted on two types of real-world datasets -- traditional and randomized trial data -- and results show that our framework can improve the recommendation performance and reduce the Simpson's paradox problem of many CF algorithms.