TY - GEN
T1 - HAMUR
T2 - 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
AU - Li, Xiaopeng
AU - Yan, Fan
AU - Zhao, Xiangyu
AU - Wang, Yichao
AU - Chen, Bo
AU - Guo, Huifeng
AU - Tang, Ruiming
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s).
PY - 2023/10/21
Y1 - 2023/10/21
N2 - 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.
AB - 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.
KW - CTR Prediction
KW - Multi-Domain Recommendation
KW - Recommendation Systems
UR - https://www.scopus.com/pages/publications/85178106123
U2 - 10.1145/3583780.3615137
DO - 10.1145/3583780.3615137
M3 - 会议稿件
AN - SCOPUS:85178106123
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1268
EP - 1277
BT - CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
Y2 - 21 October 2023 through 25 October 2023
ER -