# Deep Causal Reasoning for Recommendations

arXiv: https://arxiv.org/abs/2201.02088 · HTML: https://mlsanity.com/paper/2201.02088/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 64 references that are in the map.
- First posted on arXiv 6 Jan 2022.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [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)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [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)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Top-N Recommendation with Counterfactual User Preference Simulation](https://mlsanity.com/paper/2109.02444/) (2021)
- [On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives](https://mlsanity.com/paper/1902.10286/) (2019)
- [Unbiased Learning for the Causal Effect of Recommendation](https://mlsanity.com/paper/2008.04563/) (2020)
- [Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects](https://mlsanity.com/paper/1808.03333/) (2018)
- [Comment on "Blessings of Multiple Causes"](https://mlsanity.com/paper/1910.05438/) (2019)
- [Deconfounded Causal Collaborative Filtering](https://mlsanity.com/paper/2110.07122/) (2021)
- [Causal Collaborative Filtering](https://mlsanity.com/paper/2102.01868/) (2021)
- [Multi-Source Causal Inference Using Control Variates](https://mlsanity.com/paper/2103.16689/) (2021)
- [Towards Clarifying the Theory of the Deconfounder](https://mlsanity.com/paper/2003.04948/) (2020)

## Built on by (most cited first, 1 of 1)

- [RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs](https://mlsanity.com/paper/2508.09334/) (2025)

## Abstract (arXiv)

Traditional recommender systems aim to estimate a user's rating to an item based on observed ratings from the population. As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation. Consequently, a new trend in recommender system research is to negate the influence of confounders from a causal perspective. Observing that confounders in recommendations are usually shared among items and are therefore multi-cause confounders, we model the recommendation as a multi-cause multi-outcome (MCMO) inference problem. Specifically, to remedy confounding bias, we estimate user-specific latent variables that render the item exposures independent Bernoulli trials. The generative distribution is parameterized by a DNN with factorized logistic likelihood and the intractable posteriors are estimated by variational inference. Controlling these factors as substitute confounders, under mild assumptions, can eliminate the bias incurred by multi-cause confounders. Furthermore, we show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional causal space. Fortunately, we theoretically demonstrate that introducing user features as pre-treatment variables can substantially improve sample efficiency and alleviate overfitting. Empirical studies on simulated and real-world datasets show that the proposed deep causal recommender shows more robustness to unobserved confounders than state-of-the-art causal recommenders. Codes and datasets are released at https://github.com/yaochenzhu/deep-deconf.