EGA-V2: An End-to-end Generative Framework for Industrial Advertising
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915316938833920 |
|---|---|
| author | Zheng, Zuowu Wang, Ze Yang, Fan Fan, Jiangke Zhang, Teng Wang, Yongkang Wang, Xingxing |
| author_facet | Zheng, Zuowu Wang, Ze Yang, Fan Fan, Jiangke Zhang, Teng Wang, Yongkang Wang, Xingxing |
| contents | Traditional online industrial advertising systems suffer from the limitations of multi-stage cascaded architectures, which often discard high-potential candidates prematurely and distribute decision logic across disconnected modules. While recent generative recommendation approaches provide end-to-end solutions, they fail to address critical advertising requirements of key components for real-world deployment, such as explicit bidding, creative selection, ad allocation, and payment computation. To bridge this gap, we introduce End-to-End Generative Advertising (EGA-V2), the first unified framework that holistically models user interests, point-of-interest (POI) and creative generation, ad allocation, and payment optimization within a single generative model. Our approach employs hierarchical tokenization and multi-token prediction to jointly generate POI recommendations and ad creatives, while a permutation-aware reward model and token-level bidding strategy ensure alignment with both user experiences and advertiser objectives. Additionally, we decouple allocation from payment using a differentiable ex-post regret minimization mechanism, guaranteeing approximate incentive compatibility at the POI level. Through extensive offline evaluations we demonstrate that EGA-V2 significantly outperforms traditional cascaded systems in both performance and practicality. Our results highlight its potential as a pioneering fully generative advertising solution, paving the way for next-generation industrial ad systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17549 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EGA-V2: An End-to-end Generative Framework for Industrial Advertising Zheng, Zuowu Wang, Ze Yang, Fan Fan, Jiangke Zhang, Teng Wang, Yongkang Wang, Xingxing Information Retrieval Traditional online industrial advertising systems suffer from the limitations of multi-stage cascaded architectures, which often discard high-potential candidates prematurely and distribute decision logic across disconnected modules. While recent generative recommendation approaches provide end-to-end solutions, they fail to address critical advertising requirements of key components for real-world deployment, such as explicit bidding, creative selection, ad allocation, and payment computation. To bridge this gap, we introduce End-to-End Generative Advertising (EGA-V2), the first unified framework that holistically models user interests, point-of-interest (POI) and creative generation, ad allocation, and payment optimization within a single generative model. Our approach employs hierarchical tokenization and multi-token prediction to jointly generate POI recommendations and ad creatives, while a permutation-aware reward model and token-level bidding strategy ensure alignment with both user experiences and advertiser objectives. Additionally, we decouple allocation from payment using a differentiable ex-post regret minimization mechanism, guaranteeing approximate incentive compatibility at the POI level. Through extensive offline evaluations we demonstrate that EGA-V2 significantly outperforms traditional cascaded systems in both performance and practicality. Our results highlight its potential as a pioneering fully generative advertising solution, paving the way for next-generation industrial ad systems. |
| title | EGA-V2: An End-to-end Generative Framework for Industrial Advertising |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.17549 |