Multi-domain Recommendation with Embedding Disentangling and Domain Alignment

Ning, Wentao1,2; Yan, Xiao2; Liu, Weiwen3; Cheng, Reynold1,4,5,6; Zhang, Rui; Tang, Bo2,7,8

10.1145/3583780.3614977

2023

32nd ACM International Conference on Information and Knowledge Management (CIKM)

PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023

OCT 21-25, 2023

null,Birmingham,ENGLAND

1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES

ASSOC COMPUTING MACHINERY

Multi-domain recommendation (MDR) aims to provide recommendations for different domains (e.g., types of products) with overlapping users/items and is common for platforms such as Amazon, Facebook, and LinkedIn that host multiple services. Existing MDR models face two challenges: First, it is difficult to disentangle knowledge that generalizes across domains (e.g., a user likes cheap items) and knowledge specific to a single domain (e.g., a user likes blue clothing but not blue cars). Second, they have limited ability to transfer knowledge across domains with small overlaps. We propose a new MDR method named EDDA with two key components, i.e., embedding disentangling recommender and domain alignment, to tackle the two challenges respectively. In particular, the embedding disentangling recommender separates both the model and embedding for the inter-domain part and the intra-domain part, while most existing MDR methods only focus on model-level disentangling. The domain alignment leverages random walks from graph processing to identify similar user/item pairs from different domains and encourages similar user/item pairs to have similar embeddings, enhancing knowledge transfer. We compare EDDA with 12 state-of-the-art baselines on 3 real datasets. The results show that EDDA consistently outperforms the baselines on all datasets and domains. All datasets and codes are available at https://github.com/Stevenn9981/EDDA.

multi-domain recommendation disentanglement alignment

通讯

英语

CPCI-S

HKUTCL Joint Research Center for Artificial Intelligence[200009430] ; University of Hong Kong["104005858","10400599"] ; Guangdong-Hong Kong-Macau Joint Laboratory Program[2020B1212030009] ; Hong Kong Jockey Club Charities Trust (HKJC)[260920140] ; Shenzhen Fundamental Research Program[20220815112848002] ; Guangdong Provincial Key Laboratory[2020B121201001]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Information Systems

WOS:001161549501097

Web of Science

1.Univ Hong Kong, Hong Kong, Peoples R China
2.Southern Univ Sci & Technol, Hong Kong, Peoples R China
3.Huawei Noahs Ark Lab, Montreal, PQ, Canada
4.Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
5.Univ Hong Kong, Musketeers Fdn Inst Data Sci, Hong Kong, Peoples R China
6.Guangdong Hong Kong Macau Joint Lab, Hong Kong, Peoples R China
7.Southern Univ Sci & Technol, Res Inst Trustworthy Autonomous Syst, Shenzhen, Peoples R China
8.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Ning, Wentao,Yan, Xiao,Liu, Weiwen,et al. Multi-domain Recommendation with Embedding Disentangling and Domain Alignment[C]. 1601 Broadway, 10th Floor, NEW YORK, NY, UNITED STATES:ASSOC COMPUTING MACHINERY,2023.