HAMUR: Hyper Adapter for Multi-Domain Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915547016331264 |
|---|---|
| author | Li, Xiaopeng Yan, Fan Zhao, Xiangyu Wang, Yichao Chen, Bo Guo, Huifeng Tang, Ruiming |
| author_facet | Li, Xiaopeng Yan, Fan Zhao, Xiangyu Wang, Yichao Chen, Bo Guo, Huifeng Tang, Ruiming |
| contents | Multi-Domain Recommendation (MDR) has gained significant attention in recent years, which leverages data from multiple domains to enhance their performance concurrently.However, current MDR models are confronted with two limitations. Firstly, the majority of these models adopt an approach that explicitly shares parameters between domains, leading to mutual interference among them. Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains. To address these challenges, we propose a novel model Hyper Adapter for Multi-Domain Recommendation (HAMUR). Specifically, HAMUR consists of two components: (1). Domain-specific adapter, designed as a pluggable module that can be seamlessly integrated into various existing multi-domain backbone models, and (2). Domain-shared hyper-network, which implicitly captures shared information among domains and dynamically generates the parameters for the adapter. We conduct extensive experiments on two public datasets using various backbone networks. The experimental results validate the effectiveness and scalability of the proposed model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_06217 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | HAMUR: Hyper Adapter for Multi-Domain Recommendation Li, Xiaopeng Yan, Fan Zhao, Xiangyu Wang, Yichao Chen, Bo Guo, Huifeng Tang, Ruiming Information Retrieval Multi-Domain Recommendation (MDR) has gained significant attention in recent years, which leverages data from multiple domains to enhance their performance concurrently.However, current MDR models are confronted with two limitations. Firstly, the majority of these models adopt an approach that explicitly shares parameters between domains, leading to mutual interference among them. Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains. To address these challenges, we propose a novel model Hyper Adapter for Multi-Domain Recommendation (HAMUR). Specifically, HAMUR consists of two components: (1). Domain-specific adapter, designed as a pluggable module that can be seamlessly integrated into various existing multi-domain backbone models, and (2). Domain-shared hyper-network, which implicitly captures shared information among domains and dynamically generates the parameters for the adapter. We conduct extensive experiments on two public datasets using various backbone networks. The experimental results validate the effectiveness and scalability of the proposed model. |
| title | HAMUR: Hyper Adapter for Multi-Domain Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2309.06217 |