mlsanityData to 14 Oct 2026

DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion

arXiv 2508.14500 ↗First posted 20 Aug 2025cs.IRcited by 2

On the map: Diffusion models → Diffusion recommenders

Abstract (arXiv)

Recent advances in generative models have inspired the field of recommender systems to explore generative approaches, but most existing research focuses on sequence generation, a paradigm ill-suited for click-through rate (CTR) prediction. CTR models critically depend on a large number of cross-features between the target item and the user to estimate the probability of clicking on the item, and discarding these cross-features will significantly impair model performance. Therefore, to harness the ability of generative models to understand data distributions and thereby alleviate the constraints of traditional discriminative models in label-scarce space, diverging from the item-generation paradigm of sequence generation methods, we propose a novel sample-level generation paradigm specifically designed for the CTR task: a two-stage Discrete Diffusion-Based Generative CTR training framework (DGenCTR). This two-stage framework comprises a diffusion-based generative pre-training stage and a CTR-targeted supervised fine-tuning stage for CTR. Finally, extensive offline experiments and online A/B testing conclusively validate the effectiveness of our framework.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion recommenders, one of 14 directions in Diffusion models. Builds on 40 of its 59 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

40 of 59 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2016Wide & Deep Learning for Recommender Systemscited by 747
  6. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  7. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
  8. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  9. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 338
  10. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  11. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  12. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 278
28 more
  1. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
  2. 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 177
  3. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 173
  4. 2022Score-based Continuous-time Discrete Diffusion Modelscited by 169
  5. 2016Product-based Neural Networks for User Response Predictioncited by 145
  6. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 111
  7. 2024Learnable Item Tokenization for Generative Recommendationcited by 110
  8. 2023How to Index Item IDs for Recommendation Foundation Modelscited by 102
  9. 2019FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Predictioncited by 83
  10. 2023A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systemscited by 73
  11. 2023GenRec: Large Language Model for Generative Recommendationcited by 63
  12. 2023PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Informationcited by 60
  13. 2018Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertisingcited by 59
  14. 2024EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaborationcited by 58
  15. 2024IDGenRec: LLM-RecSys Alignment with Textual ID Learningcited by 53
  16. 2025MTGR: Industrial-Scale Generative Recommendation Framework in Meituancited by 49
  17. 2021MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Maskcited by 48
  18. 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representationscited by 35
  19. 2021Deep Learning for Click-Through Rate Estimationcited by 33
  20. 2023On the Embedding Collapse when Scaling up Recommendation Modelscited by 29
  21. 2024CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendationcited by 24
  22. 2022Joint Optimization of Ranking and Calibration with Contextualized Hybrid Modelcited by 22
  23. 2021Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Predictioncited by 21
  24. 2023Towards Deeper, Lighter and Interpretable Cross Network for CTR Predictioncited by 20
  25. 2022Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendationcited by 19
  26. 2024Heavy-Tailed Diffusion with Denoising L'evy Probabilistic Modelscited by 18
  27. 2022Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Frameworkcited by 13
  28. 2024Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Pathscited by 0
  2. 2026Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Explorationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
  2. 2025Addressing Cold-start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling
  3. 2023Discrete Conditional Diffusion for Reranking in Recommendation
  4. 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendation
  5. 2023MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction
  6. 2024DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models
  7. 2026Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation
  8. 2026Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation