mlsanityData to 7 Oct 2026

Recommendations as Treatments: Debiasing Learning and Evaluation

arXiv 1602.05352 ↗First posted 17 Feb 2016cs.LG cs.AI cs.IRcited by 246

Not on the map. Why?

Abstract (arXiv)

Most data for evaluating and training recommender systems is subject to selection biases, either through self-selection by the users or through the actions of the recommendation system itself. In this paper, we provide a principled approach to handling selection biases, adapting models and estimation techniques from causal inference. The approach leads to unbiased performance estimators despite biased data, and to a matrix factorization method that provides substantially improved prediction performance on real-world data. We theoretically and empirically characterize the robustness of the approach, finding that it is highly practical and scalable.

Key facts. Cited by 246 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 53; 2023: 51; 2024: 34; 2025: 31; 2026: 40.

246 papers.

Sort:

By area:

  1. 2023Data Distillation: A Surveycited by 86
  2. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  3. 2021AutoDebias: Learning to Debias for Recommendationcited by 68
  4. 2022ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimationcited by 47
  5. 2021Causal Matrix Completioncited by 45
  6. 2024CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendationcited by 44
  7. 2023A Survey on Popularity Bias in Recommender Systemscited by 42
  8. 2021SurvTRACE: Transformers for Survival Analysis with Competing Eventscited by 40
  9. 2021Understanding the role of importance weighting for deep learningcited by 38
  10. 2022Anticipating Performativity by Predicting from Predictionscited by 37
  11. 2022Generalized Strategic Classification and the Case of Aligned Incentivescited by 34
  12. 2022Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequalitycited by 32
38 more
  1. 2023A Trip Towards Fairness: Bias and De-Biasing in Large Language Modelscited by 32
  2. 2021Identifiable Generative Models for Missing Not at Random Data Imputationcited by 30
  3. 2023RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agentscited by 30
  4. 2021Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimationcited by 28
  5. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  6. 2022StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Randomcited by 24
  7. 2021Policy Learning with Adaptively Collected Datacited by 21
  8. 2021Top-N Recommendation with Counterfactual User Preference Simulationcited by 21
  9. 2022Fair ranking: a critical review, challenges, and future directionscited by 21
  10. 2022Trustworthy Recommender Systemscited by 21
  11. 2024How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspectivecited by 21
  12. 2022Infinite Recommendation Networks: A Data-Centric Approachcited by 20
  13. 2021A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directionscited by 19
  14. 2022TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendationscited by 18
  15. 2022Respecting Transfer Gap in Knowledge Distillationcited by 18
  16. 2022A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Predictioncited by 18
  17. 2023Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendationscited by 18
  18. 2021Correcting Exposure Bias for Link Recommendationcited by 17
  19. 2022CausPref: Causal Preference Learning for Out-of-Distribution Recommendationcited by 17
  20. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  21. 2021Obtaining Calibrated Probabilities with Personalized Ranking Modelscited by 15
  22. 2023Importance-Weighted Offline Learning Done Rightcited by 15
  23. 2021On component interactions in two-stage recommender systemscited by 14
  24. 2021Deconfounded Causal Collaborative Filteringcited by 14
  25. 2022Breaking Feedback Loops in Recommender Systems with Causal Inferencecited by 14
  26. 2023A Survey on Fairness-aware Recommender Systemscited by 14
  27. 2023Off-Policy Evaluation for Large Action Spaces via Policy Convolutioncited by 14
  28. 2021Causal Collaborative Filteringcited by 13
  29. 2021Multi-Source Causal Inference Using Control Variatescited by 13
  30. 2022Entire Space Counterfactual Learning for Reliable Content Recommendationscited by 13
  31. 2022Causal Disentanglement for Semantics-Aware Intent Learning in Recommendationcited by 12
  32. 2022Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservicescited by 12
  33. 2023Robust Collaborative Filtering to Popularity Distribution Shiftcited by 12
  34. 2022Multiple Robust Learning for Recommendationcited by 11
  35. 2022Unbiased Knowledge Distillation for Recommendationcited by 11
  36. 2023Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobaocited by 11
  37. 2024Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patientscited by 11
  38. 2024Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendationscited by 11

50 most cited of 246 All 246 (JSON)