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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Moyu, Chen, Yun, Jin, Yujun, Hu, Jinxin, Zhang, Yu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912555934416896
author Zhang, Moyu
Chen, Yun
Jin, Yujun
Hu, Jinxin
Zhang, Yu
author_facet Zhang, Moyu
Chen, Yun
Jin, Yujun
Hu, Jinxin
Zhang, Yu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion
Zhang, Moyu
Chen, Yun
Jin, Yujun
Hu, Jinxin
Zhang, Yu
Information Retrieval
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.
title DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion
topic Information Retrieval
url https://arxiv.org/abs/2508.14500