# Top-N Recommendation with Counterfactual User Preference Simulation

arXiv: https://arxiv.org/abs/2109.02444 · HTML: https://mlsanity.com/paper/2109.02444/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [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)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms](https://mlsanity.com/paper/2011.01731/) (2020)
- [Causal Embeddings for Recommendation](https://mlsanity.com/paper/1706.07639/) (2017)
- [Specifying Object Attributes and Relations in Interactive Scene Generation](https://mlsanity.com/paper/1909.05379/) (2019)
- [IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models](https://mlsanity.com/paper/1705.10513/) (2017)
- [Counterfactual Critic Multi-Agent Training for Scene Graph Generation](https://mlsanity.com/paper/1812.02347/) (2018)
- [Adversarial Personalized Ranking for Recommendation](https://mlsanity.com/paper/1808.03908/) (2018)
- [Deep Reinforcement Learning for List-wise Recommendations](https://mlsanity.com/paper/1801.00209/) (2017)
- [Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling](https://mlsanity.com/paper/1911.07308/) (2019)
- [DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction](https://mlsanity.com/paper/1804.04950/) (2018)
- [FairyTED: A Fair Rating Predictor for TED Talk Data](https://mlsanity.com/paper/1911.11558/) (2019)

## Built on by (most cited first, 21 of 21)

- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation](https://mlsanity.com/paper/2204.05125/) (2022)
- [Deconfounded Causal Collaborative Filtering](https://mlsanity.com/paper/2110.07122/) (2021)
- [Unbiased Knowledge Distillation for Recommendation](https://mlsanity.com/paper/2211.14729/) (2022)
- [Debiased Recommendation with Noisy Feedback](https://mlsanity.com/paper/2406.17182/) (2024)
- [Learning Explicit User Interest Boundary for Recommendation](https://mlsanity.com/paper/2111.11026/) (2021)
- [Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems](https://mlsanity.com/paper/2505.16429/) (2025)
- [Causal Disentanglement with Network Information for Debiased Recommendations](https://mlsanity.com/paper/2204.07221/) (2022)
- [Curious Causality-Seeking Agents Learn Meta Causal World](https://mlsanity.com/paper/2506.23068/) (2025)
- [Counterfactual Collaborative Reasoning](https://mlsanity.com/paper/2307.00165/) (2023)
- [Specify Robust Causal Representation from Mixed Observations](https://mlsanity.com/paper/2310.13892/) (2023)
- [Dynamic Causal Collaborative Filtering](https://mlsanity.com/paper/2208.11094/) (2022)
- [Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation](https://mlsanity.com/paper/2304.05615/) (2023)
- [Deep Causal Reasoning for Recommendations](https://mlsanity.com/paper/2201.02088/) (2022)
- [The Importance of Causality in Decision Making: A Perspective on Recommender Systems](https://mlsanity.com/paper/2410.01822/) (2024)
- [Guided Diffusion-based Counterfactual Augmentation for Robust Session-based Recommendation](https://mlsanity.com/paper/2410.21892/) (2024)
- [Generalizable Information Theoretic Causal Representation](https://mlsanity.com/paper/2202.08388/) (2022)
- [Explainable History Distillation by Marked Temporal Point Process](https://mlsanity.com/paper/2311.07797/) (2023)
- [Causal Discovery in Recommender Systems: Example and Discussion](https://mlsanity.com/paper/2409.10271/) (2024)
- [On Predicting Post-Click Conversion Rate via Counterfactual Inference](https://mlsanity.com/paper/2510.04816/) (2025)
- [Causality Enhancement for Cross-Domain Recommendation](https://mlsanity.com/paper/2510.14641/) (2025)

## Abstract (arXiv)

Top-N recommendation, which aims to learn user ranking-based preference, has long been a fundamental problem in a wide range of applications. Traditional models usually motivate themselves by designing complex or tailored architectures based on different assumptions. However, the training data of recommender system can be extremely sparse and imbalanced, which poses great challenges for boosting the recommendation performance. To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem. The core of our model lies in the counterfactual question: "what would be the user's decision if the recommended items had been different?". To answer this question, we firstly formulate the recommendation process with a series of structural equation models (SEMs), whose parameters are optimized based on the observed data. Then, we actively indicate many recommendation lists (called intervention in the causal inference terminology) which are not recorded in the dataset, and simulate user feedback according to the learned SEMs for generating new training samples. Instead of randomly intervening on the recommendation list, we design a learning-based method to discover more informative training samples. Considering that the learned SEMs can be not perfect, we, at last, theoretically analyze the relation between the number of generated samples and the model prediction error, based on which a heuristic method is designed to control the negative effect brought by the prediction error. Extensive experiments are conducted based on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.