EGA-V1: Unifying Online Advertising with End-to-End Learning
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_ | 1866909631502090240 |
|---|---|
| author | Qiu, Junyan Wang, Ze Zhang, Fan Zheng, Zuowu Zhu, Jile Fan, Jiangke Zhang, Teng Wang, Haitao Wang, Yongkang Wang, Xingxing |
| author_facet | Qiu, Junyan Wang, Ze Zhang, Fan Zheng, Zuowu Zhu, Jile Fan, Jiangke Zhang, Teng Wang, Haitao Wang, Yongkang Wang, Xingxing |
| contents | Modern industrial advertising systems commonly employ Multi-stage Cascading Architectures (MCA) to balance computational efficiency with ranking accuracy. However, this approach presents two fundamental challenges: (1) performance inconsistencies arising from divergent optimization targets and capability differences between stages, and (2) failure to account for advertisement externalities - the complex interactions between candidate ads during ranking. These limitations ultimately compromise system effectiveness and reduce platform profitability. In this paper, we present EGA-V1, an end-to-end generative architecture that unifies online advertising ranking as one model. EGA-V1 replaces cascaded stages with a single model to directly generate optimal ad sequences from the full candidate ad corpus in location-based services (LBS). The primary challenges associated with this approach stem from high costs of feature processing and computational bottlenecks in modeling externalities of large-scale candidate pools. To address these challenges, EGA-V1 introduces an algorithm and engine co-designed hybrid feature service to decouple user and ad feature processing, reducing latency while preserving expressiveness. To efficiently extract intra- and cross-sequence mutual information, we propose RecFormer with an innovative cluster-attention mechanism as its core architectural component. Furthermore, we propose a bi-stage training strategy that integrates pre-training with reinforcement learning-based post-training to meet sophisticated platform and advertising objectives. Extensive offline evaluations on public benchmarks and large-scale online A/B testing on industrial advertising platform have demonstrated the superior performance of EGA-V1 over state-of-the-art MCAs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19755 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EGA-V1: Unifying Online Advertising with End-to-End Learning Qiu, Junyan Wang, Ze Zhang, Fan Zheng, Zuowu Zhu, Jile Fan, Jiangke Zhang, Teng Wang, Haitao Wang, Yongkang Wang, Xingxing Information Retrieval Modern industrial advertising systems commonly employ Multi-stage Cascading Architectures (MCA) to balance computational efficiency with ranking accuracy. However, this approach presents two fundamental challenges: (1) performance inconsistencies arising from divergent optimization targets and capability differences between stages, and (2) failure to account for advertisement externalities - the complex interactions between candidate ads during ranking. These limitations ultimately compromise system effectiveness and reduce platform profitability. In this paper, we present EGA-V1, an end-to-end generative architecture that unifies online advertising ranking as one model. EGA-V1 replaces cascaded stages with a single model to directly generate optimal ad sequences from the full candidate ad corpus in location-based services (LBS). The primary challenges associated with this approach stem from high costs of feature processing and computational bottlenecks in modeling externalities of large-scale candidate pools. To address these challenges, EGA-V1 introduces an algorithm and engine co-designed hybrid feature service to decouple user and ad feature processing, reducing latency while preserving expressiveness. To efficiently extract intra- and cross-sequence mutual information, we propose RecFormer with an innovative cluster-attention mechanism as its core architectural component. Furthermore, we propose a bi-stage training strategy that integrates pre-training with reinforcement learning-based post-training to meet sophisticated platform and advertising objectives. Extensive offline evaluations on public benchmarks and large-scale online A/B testing on industrial advertising platform have demonstrated the superior performance of EGA-V1 over state-of-the-art MCAs. |
| title | EGA-V1: Unifying Online Advertising with End-to-End Learning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.19755 |