Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912602506919936 |
|---|---|
| author | Zhao, Qihang Zheng, Xiaoyang Chen, Ben Sun, Zhongbo Lei, Chenyi |
| author_facet | Zhao, Qihang Zheng, Xiaoyang Chen, Ben Sun, Zhongbo Lei, Chenyi |
| contents | User behavior sequences in search systems resemble "interest fossils", capturing genuine intent yet eroded by exposure bias, category drift, and contextual noise. Current methods predominantly follow an "identify-aggregate" paradigm, assuming sequences immutably reflect user preferences while overlooking the organic entanglement of noise and genuine interest. Moreover, they output static, context-agnostic representations, failing to adapt to dynamic intent shifts under varying Query-User-Item-Context conditions.
To resolve this dual challenge, we propose the Contextual Diffusion Purifier (CDP). By treating category-filtered behaviors as "contaminated observations", CDP employs a forward noising and conditional reverse denoising process guided by cross-interaction features (Query x User x Item x Context), controllably generating pure, context-aware interest representations that dynamically evolve with scenarios. Extensive offline/online experiments demonstrate the superiority of CDP over state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19876 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Prediction Zhao, Qihang Zheng, Xiaoyang Chen, Ben Sun, Zhongbo Lei, Chenyi Information Retrieval User behavior sequences in search systems resemble "interest fossils", capturing genuine intent yet eroded by exposure bias, category drift, and contextual noise. Current methods predominantly follow an "identify-aggregate" paradigm, assuming sequences immutably reflect user preferences while overlooking the organic entanglement of noise and genuine interest. Moreover, they output static, context-agnostic representations, failing to adapt to dynamic intent shifts under varying Query-User-Item-Context conditions. To resolve this dual challenge, we propose the Contextual Diffusion Purifier (CDP). By treating category-filtered behaviors as "contaminated observations", CDP employs a forward noising and conditional reverse denoising process guided by cross-interaction features (Query x User x Item x Context), controllably generating pure, context-aware interest representations that dynamically evolve with scenarios. Extensive offline/online experiments demonstrate the superiority of CDP over state-of-the-art methods. |
| title | Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Prediction |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2509.19876 |