GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911042675671040 |
|---|---|
| author | Xu, Wei Li, Haoran Ou, Baoyuan Xu, Lai Qin, Yingjie Su, Ruilong Xu, Ruiwen |
| author_facet | Xu, Wei Li, Haoran Ou, Baoyuan Xu, Lai Qin, Yingjie Su, Ruilong Xu, Ruiwen |
| contents | Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains to a target domain. Most existing methods rely on overlapping users to facilitate this transfer, often focusing on joint training or pre-training with fine-tuning approach to connect the source and target domains. However, in real-world industrial settings, joint training struggles to learn optimal representations with different distributions, and pre-training with fine-tuning is not well-suited for continuously integrating new data. To address these issues, we propose GIST, a cross-domain lifelong sequence model that decouples the training processes of the source and target domains. Unlike previous methods that search lifelong sequences in the source domains using only content or behavior signals or their simple combinations, we innovatively introduce a Content-Behavior Joint Training Module (CBJT), which aligns content-behavior distributions and combines them with guided information to facilitate a more stable representation. Furthermore, we develop an Asymmetric Similarity Integration strategy (ASI) to augment knowledge transfer through similarity computation. Extensive experiments demonstrate the effectiveness of GIST, surpassing SOTA methods on offline evaluations and an online A/B test. Deployed on the Xiaohongshu (RedNote) platform, GIST effectively enhances online ads system performance at scale, serving hundreds of millions of daily active users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation Xu, Wei Li, Haoran Ou, Baoyuan Xu, Lai Qin, Yingjie Su, Ruilong Xu, Ruiwen Artificial Intelligence Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains to a target domain. Most existing methods rely on overlapping users to facilitate this transfer, often focusing on joint training or pre-training with fine-tuning approach to connect the source and target domains. However, in real-world industrial settings, joint training struggles to learn optimal representations with different distributions, and pre-training with fine-tuning is not well-suited for continuously integrating new data. To address these issues, we propose GIST, a cross-domain lifelong sequence model that decouples the training processes of the source and target domains. Unlike previous methods that search lifelong sequences in the source domains using only content or behavior signals or their simple combinations, we innovatively introduce a Content-Behavior Joint Training Module (CBJT), which aligns content-behavior distributions and combines them with guided information to facilitate a more stable representation. Furthermore, we develop an Asymmetric Similarity Integration strategy (ASI) to augment knowledge transfer through similarity computation. Extensive experiments demonstrate the effectiveness of GIST, surpassing SOTA methods on offline evaluations and an online A/B test. Deployed on the Xiaohongshu (RedNote) platform, GIST effectively enhances online ads system performance at scale, serving hundreds of millions of daily active users. |
| title | GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.05142 |