mlsanityData to 7 Oct 2026

Entire Space Counterfactual Learning for Reliable Content Recommendations

arXiv 2210.11039 ↗First posted 20 Oct 2022cs.LG cs.AI stat.MLcited by 13

Not on the map. Why?

Abstract (arXiv)

Post-click conversion rate (CVR) estimation is a fundamental task in developing effective recommender systems, yet it faces challenges from data sparsity and sample selection bias. To handle both challenges, the entire space multitask models are employed to decompose the user behavior track into a sequence of exposure rightarrow click rightarrow conversion, constructing surrogate learning tasks for CVR estimation. However, these methods suffer from two significant defects: (1) intrinsic estimation bias (IEB), where the CVR estimates are higher than the actual values; (2) false independence prior (FIP), where the causal relationship between clicks and subsequent conversions is potentially overlooked. To overcome these limitations, we develop a model-agnostic framework, namely Entire Space Counterfactual Multitask Model (ESCM2), which incorporates a counterfactual risk minimizer within the ESMM framework to regularize CVR estimation. Experiments conducted on large-scale industrial recommendation datasets and an online industrial recommendation service demonstrate that ESCM2 effectively mitigates IEB and FIP defects and substantially enhances recommendation performance.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 21 of its 54 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

21 of 54 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  3. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 246
  4. 2018Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Ratecited by 172
  5. 2016Unbiased Learning-to-Rank with Biased Feedbackcited by 155
  6. 2019Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedbackcited by 79
  7. 2021AutoDebias: Learning to Debias for Recommendationcited by 68
  8. 2022ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimationcited by 47
  9. 2022Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendationcited by 42
  10. 2019Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learningcited by 39
  11. 2021Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertisingcited by 39
  12. 2022Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Modelscited by 33
9 more
  1. 2020ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performancecited by 30
  2. 2020Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedbackcited by 30
  3. 2019Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedbackcited by 28
  4. 2021Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimationcited by 28
  5. 2021Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Predictioncited by 21
  6. 2022Multiple Robust Learning for Recommendationcited by 11
  7. 2022A Multi-task Learning Framework for Product Ranking with BERTcited by 7
  8. 2017Identifying Clickbait: A Multi-Strategy Approach Using Neural Networkscited by 4
  9. 2022Multi-Scale User Behavior Network for Entire Space Multi-Task Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 7; 2026: 3.

13 papers.

Sort:

By area:

  1. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  2. 2024FreDF: Learning to Forecast in the Frequency Domaincited by 77
  3. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 58
  4. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
  5. 2025Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewardscited by 11
  6. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  7. 2024Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimationcited by 7
  8. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 7
  9. 2026CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbackscited by 6
  10. 2025DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoringcited by 5
  11. 2026ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignmentcited by 2
  12. 2025Addressing Correlated Latent Exogenous Variables in Debiased Recommender Systemscited by 0
1 more
  1. 2026Slack More, Predict Better: Proximal Relaxation for Probabilistic Latent Variable Model-based Soft Sensorscited by 0