mlsanityData to 14 Oct 2026

Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobao

arXiv 2306.03527 ↗First posted 6 Jun 2023cs.IR cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Click-Through Rate (CTR) prediction serves as a fundamental component in online advertising. A common practice is to train a CTR model on advertisement (ad) impressions with user feedback. Since ad impressions are purposely selected by the model itself, their distribution differs from the inference distribution and thus exhibits sample selection bias (SSB) that affects model performance. Existing studies on SSB mainly employ sample re-weighting techniques which suffer from high variance and poor model calibration. Another line of work relies on costly uniform data that is inadequate to train industrial models. Thus mitigating SSB in industrial models with a uniform-data-free framework is worth exploring. Fortunately, many platforms display mixed results of organic items (i.e., recommendations) and sponsored items (i.e., ads) to users, where impressions of ads and recommendations are selected by different systems but share the same user decision rationales. Based on the above characteristics, we propose to leverage recommendations samples as a free lunch to mitigate SSB for ads CTR model (Rec4Ad). After elaborating data augmentation, Rec4Ad learns disentangled representations with alignment and decorrelation modules for enhancement. When deployed in Taobao display advertising system, Rec4Ad achieves substantial gains in key business metrics, with a lift of up to +6.6% CTR and +2.9% RPM.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

24 of 42 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  4. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  5. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  6. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  7. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 278
  8. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 248
  9. 2016Unbiased Learning-to-Rank with Biased Feedbackcited by 157
  10. 2021Causal Intervention for Leveraging Popularity Bias in Recommendationcited by 116
  11. 2015Reducing Overfitting in Deep Networks by Decorrelating Representationscited by 94
  12. 2017Causal Embeddings for Recommendationcited by 79
12 more
  1. 2021One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Predictioncited by 78
  2. 2020Correcting for Selection Bias in Learning-to-rank Systemscited by 35
  3. 2022On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Modelscited by 34
  4. 2022Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Modelscited by 33
  5. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  6. 2022Joint Optimization of Ranking and Calibration with Contextualized Hybrid Modelcited by 22
  7. 2014Discovering Hidden Factors of Variation in Deep Networkscited by 21
  8. 2022Adaptive Domain Interest Network for Multi-domain Recommendationcited by 20
  9. 2022A Model-Agnostic Causal Learning Framework for Recommendation using Search Datacited by 17
  10. 2022PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systemscited by 17
  11. 2022KEEP: An Industrial Pre-Training Framework for Online Recommendation via Knowledge Extraction and Pluggingcited by 11
  12. 2019Learning to Advertise for Organic Traffic Maximization in E-Commerce Product Feedscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 7; 2026: 2.

11 papers.

  1. 2025To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBaycited by 4
  2. 2023ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraintcited by 3
  3. 2024GraphEx: A Graph-based Extraction Method for Advertiser Keyphrase Recommendationcited by 3
  4. 2025The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversioncited by 3
  5. 2025LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBaycited by 2
  6. 2026Causal Representation Learning for Generalisable Recommendationcited by 2
  7. 2025BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendationscited by 1
  8. 2025Multi-Faceted Large Embedding Tables for Pinterest Ads Rankingcited by 1
  9. 2025A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systemscited by 0
  10. 2025Facets of Disparate Impact: Evaluating Legally Consistent Bias in Machine Learningcited by 0
  11. 2026Generative Pseudo-Labeling for Pre-Ranking with LLMscited by 0