Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914303956746240 |
|---|---|
| author | Liu, Jiahao Ruan, Hongji Zhang, Weimin Tong, Ziye Tang, Derick Zeng, Zhanpeng Zeng, Qinsong Zhang, Peng Lu, Tun Gu, Ning |
| author_facet | Liu, Jiahao Ruan, Hongji Zhang, Weimin Tong, Ziye Tang, Derick Zeng, Zhanpeng Zeng, Qinsong Zhang, Peng Lu, Tun Gu, Ning |
| contents | This paper explores effective numerical feature embedding for Click-Through Rate prediction in streaming environments. Conventional static binning methods rely on offline statistics of numerical distributions; however, this inherently two-stage process often triggers semantic drift during bin boundary updates. While neural embedding methods enable end-to-end learning, they often discard explicit distributional information. Integrating such information end-to-end is challenging because streaming features often violate the i.i.d. assumption, precluding unbiased estimation of the population distribution via the expectation of order statistics. Furthermore, the critical context dependency of numerical distributions is often neglected. To this end, we propose DAES, an end-to-end framework designed to tackle numerical feature embedding in streaming training scenarios by integrating distributional information with an adaptive modulation mechanism. Specifically, we introduce an efficient reservoir-sampling-based distribution estimation method and two field-aware distribution modulation strategies to capture streaming distributions and field-dependent semantics. DAES significantly outperforms existing approaches as demonstrated by extensive offline and online experiments and has been fully deployed on a leading short-video platform with hundreds of millions of daily active users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03223 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction Liu, Jiahao Ruan, Hongji Zhang, Weimin Tong, Ziye Tang, Derick Zeng, Zhanpeng Zeng, Qinsong Zhang, Peng Lu, Tun Gu, Ning Information Retrieval Artificial Intelligence This paper explores effective numerical feature embedding for Click-Through Rate prediction in streaming environments. Conventional static binning methods rely on offline statistics of numerical distributions; however, this inherently two-stage process often triggers semantic drift during bin boundary updates. While neural embedding methods enable end-to-end learning, they often discard explicit distributional information. Integrating such information end-to-end is challenging because streaming features often violate the i.i.d. assumption, precluding unbiased estimation of the population distribution via the expectation of order statistics. Furthermore, the critical context dependency of numerical distributions is often neglected. To this end, we propose DAES, an end-to-end framework designed to tackle numerical feature embedding in streaming training scenarios by integrating distributional information with an adaptive modulation mechanism. Specifically, we introduce an efficient reservoir-sampling-based distribution estimation method and two field-aware distribution modulation strategies to capture streaming distributions and field-dependent semantics. DAES significantly outperforms existing approaches as demonstrated by extensive offline and online experiments and has been fully deployed on a leading short-video platform with hundreds of millions of daily active users. |
| title | Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2602.03223 |