File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
Title | Multi-domain Recommendation with Embedding Disentangling and Domain Alignment |
---|---|
Authors | |
Issue Date | 21-Oct-2023 |
Publisher | ACM |
Abstract | 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. |
Persistent Identifier | http://hdl.handle.net/10722/339108 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ning, Wentao | - |
dc.contributor.author | Yan, Xiao | - |
dc.contributor.author | Liu, Weiwen | - |
dc.contributor.author | Cheng, Reynold | - |
dc.contributor.author | Zhang, Rui | - |
dc.contributor.author | Tang, Bo | - |
dc.date.accessioned | 2024-03-11T10:33:57Z | - |
dc.date.available | 2024-03-11T10:33:57Z | - |
dc.date.issued | 2023-10-21 | - |
dc.identifier.uri | http://hdl.handle.net/10722/339108 | - |
dc.description.abstract | <p>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.<br></p> | - |
dc.language | eng | - |
dc.publisher | ACM | - |
dc.relation.ispartof | 32nd ACM International Conference on Information and Knowledge Management (21/10/2023-25/10/2023, Birmingham ) | - |
dc.title | Multi-domain Recommendation with Embedding Disentangling and Domain Alignment | - |
dc.type | Conference_Paper | - |
dc.identifier.doi | 10.1145/3583780.3614977 | - |