Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2408.01332 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909278195941376 |
|---|---|
| author | Lou, Xingyu Yang, Yu Dong, Kuiyao Huang, Heyuan Yu, Wenyi Wang, Ping Li, Xiu Wang, Jun |
| author_facet | Lou, Xingyu Yang, Yu Dong, Kuiyao Huang, Heyuan Yu, Wenyi Wang, Ping Li, Xiu Wang, Jun |
| contents | As the recommendation service needs to address increasingly diverse distributions, such as multi-population, multi-scenario, multitarget, and multi-interest, more and more recent works have focused on multi-distribution modeling and achieved great progress. However, most of them only consider modeling in a single multi-distribution manner, ignoring that mixed multi-distributions often coexist and form hierarchical relationships. To address these challenges, we propose a flexible modeling paradigm, named Hierarchical Multi-Distribution Network (HMDN), which efficiently models these hierarchical relationships and can seamlessly integrate with existing multi-distribution methods, such as Mixture of-Experts (MoE) and Dynamic-Weight (DW) models. Specifically, we first design a hierarchical multi-distribution representation refinement module, employing a multi-level residual quantization to obtain fine-grained hierarchical representation. Then, the refined hierarchical representation is integrated into the existing single multi-distribution models, seamlessly expanding them into mixed multi-distribution models. Experimental results on both public and industrial datasets validate the effectiveness and flexibility of HMDN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction Lou, Xingyu Yang, Yu Dong, Kuiyao Huang, Heyuan Yu, Wenyi Wang, Ping Li, Xiu Wang, Jun Machine Learning As the recommendation service needs to address increasingly diverse distributions, such as multi-population, multi-scenario, multitarget, and multi-interest, more and more recent works have focused on multi-distribution modeling and achieved great progress. However, most of them only consider modeling in a single multi-distribution manner, ignoring that mixed multi-distributions often coexist and form hierarchical relationships. To address these challenges, we propose a flexible modeling paradigm, named Hierarchical Multi-Distribution Network (HMDN), which efficiently models these hierarchical relationships and can seamlessly integrate with existing multi-distribution methods, such as Mixture of-Experts (MoE) and Dynamic-Weight (DW) models. Specifically, we first design a hierarchical multi-distribution representation refinement module, employing a multi-level residual quantization to obtain fine-grained hierarchical representation. Then, the refined hierarchical representation is integrated into the existing single multi-distribution models, seamlessly expanding them into mixed multi-distribution models. Experimental results on both public and industrial datasets validate the effectiveness and flexibility of HMDN. |
| title | HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2408.01332 |