# Deconfounded Causal Collaborative Filtering

arXiv: https://arxiv.org/abs/2110.07122 · HTML: https://mlsanity.com/paper/2110.07122/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 65 references that are in the map.
- First posted on arXiv 14 Oct 2021.

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

- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [The Blessings of Multiple Causes](https://mlsanity.com/paper/1805.06826/) (2018)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [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)
- [Towards Long-term Fairness in Recommendation](https://mlsanity.com/paper/2101.03584/) (2021)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [Unbiased Learning to Rank with Unbiased Propensity Estimation](https://mlsanity.com/paper/1804.05938/) (2018)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Graphical Models for Processing Missing Data](https://mlsanity.com/paper/1801.03583/) (2018)
- [Deconfounded Recommendation for Alleviating Bias Amplification](https://mlsanity.com/paper/2105.10648/) (2021)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Correcting for Selection Bias in Learning-to-rank Systems](https://mlsanity.com/paper/2001.11358/) (2020)
- [The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation](https://mlsanity.com/paper/2008.09273/) (2020)
- [Estimating Position Bias without Intrusive Interventions](https://mlsanity.com/paper/1812.05161/) (2018)
- [Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback](https://mlsanity.com/paper/1910.01444/) (2019)
- [Multi-sided Exposure Bias in Recommendation](https://mlsanity.com/paper/2006.15772/) (2020)
- [Top-N Recommendation with Counterfactual User Preference Simulation](https://mlsanity.com/paper/2109.02444/) (2021)
- [Correcting Exposure Bias for Link Recommendation](https://mlsanity.com/paper/2106.07041/) (2021)
- [Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation](https://mlsanity.com/paper/1907.06584/) (2019)
- [Cascade Model-based Propensity Estimation for Counterfactual Learning to Rank](https://mlsanity.com/paper/2005.11938/) (2020)
- [Counterfactual Evaluation for Explainable AI](https://mlsanity.com/paper/2109.01962/) (2021)
- [Causal Collaborative Filtering](https://mlsanity.com/paper/2102.01868/) (2021)
- [CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation](https://mlsanity.com/paper/2107.02390/) (2021)

## Built on by (most cited first, 14 of 14)

- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Rating Sentiment Analysis Systems for Bias through a Causal Lens](https://mlsanity.com/paper/2302.02038/) (2023)
- [Advances in Automatically Rating the Trustworthiness of Text Processing Services](https://mlsanity.com/paper/2302.09079/) (2023)
- [The Effect of Human v/s Synthetic Test Data and Round-tripping on Assessment of Sentiment Analysis Systems for Bias](https://mlsanity.com/paper/2401.12985/) (2024)
- [Dynamic Causal Collaborative Filtering](https://mlsanity.com/paper/2208.11094/) (2022)
- [Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation](https://mlsanity.com/paper/2403.03578/) (2024)
- [Deep Causal Reasoning for Recommendations](https://mlsanity.com/paper/2201.02088/) (2022)
- [Causal Structure Representation Learning of Confounders in Latent Space for Recommendation](https://mlsanity.com/paper/2311.03382/) (2023)
- [Review of Explainable Graph-Based Recommender Systems](https://mlsanity.com/paper/2408.00166/) (2024)
- [The Importance of Causality in Decision Making: A Perspective on Recommender Systems](https://mlsanity.com/paper/2410.01822/) (2024)
- [Towards a Theoretical Understanding of Two Tower Recommendation Models](https://mlsanity.com/paper/2403.00802/) (2024)
- [Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation](https://mlsanity.com/paper/2510.04502/) (2025)
- [Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation](https://mlsanity.com/paper/2601.21335/) (2026)

## Abstract (arXiv)

Recommender systems may be confounded by various types of confounding factors (also called confounders) that may lead to inaccurate recommendations and sacrificed recommendation performance. Current approaches to solving the problem usually design each specific model for each specific confounder. However, real-world systems may include a huge number of confounders and thus designing each specific model for each specific confounder could be unrealistic. More importantly, except for those ``explicit confounders'' that experts can manually identify and process such as item's position in the ranking list, there are also many ``latent confounders'' that are beyond the imagination of experts. For example, users' rating on a song may depend on their current mood or the current weather, and users' preference on ice creams may depend on the air temperature. Such latent confounders may be unobservable in the recorded training data. To solve the problem, we propose Deconfounded Causal Collaborative Filtering (DCCF). We first frame user behaviors with unobserved confounders into a causal graph, and then we design a front-door adjustment model carefully fused with machine learning to deconfound the influence of unobserved confounders. Experiments on real-world datasets show that our method is able to deconfound unobserved confounders to achieve better recommendation performance.