Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386875129> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4386875129 abstract "In modern commercial search engines and recommendation systems, data from multiple domains is available to jointly train the multi-domain model. Traditional methods train multi-domain models in the multi-task setting, with shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of features, labels, and sample distributions of individual tasks. With the development of large language models, LLM can extract global domain-invariant text features that serve both search and recommendation tasks. We propose a novel framework called S&R Multi-Domain Foundation, which uses LLM to extract domain invariant features, and Aspect Gating Fusion to merge the ID feature, domain invariant text features and task-specific heterogeneous sparse features to obtain the representations of query and item. Additionally, samples from multiple search and recommendation scenarios are trained jointly with Domain Adaptive Multi-Task module to obtain the multi-domain foundation model. We apply the S&R Multi-Domain foundation model to cold start scenarios in the pretrain-finetune manner, which achieves better performance than other SOTA transfer learning methods. The S&R Multi-Domain Foundation model has been successfully deployed in Alipay Mobile Application's online services, such as content query recommendation and service card recommendation, etc." @default.
- W4386875129 created "2023-09-20" @default.
- W4386875129 creator A5003312894 @default.
- W4386875129 creator A5022905256 @default.
- W4386875129 creator A5028498756 @default.
- W4386875129 creator A5031338085 @default.
- W4386875129 creator A5041779682 @default.
- W4386875129 creator A5080106267 @default.
- W4386875129 date "2023-09-16" @default.
- W4386875129 modified "2023-09-27" @default.
- W4386875129 title "An Unified Search and Recommendation Foundation Model for Cold-Start Scenario" @default.
- W4386875129 doi "https://doi.org/10.1145/3583780.3614657" @default.
- W4386875129 hasPublicationYear "2023" @default.
- W4386875129 type Work @default.
- W4386875129 citedByCount "0" @default.
- W4386875129 crossrefType "posted-content" @default.
- W4386875129 hasAuthorship W4386875129A5003312894 @default.
- W4386875129 hasAuthorship W4386875129A5022905256 @default.
- W4386875129 hasAuthorship W4386875129A5028498756 @default.
- W4386875129 hasAuthorship W4386875129A5031338085 @default.
- W4386875129 hasAuthorship W4386875129A5041779682 @default.
- W4386875129 hasAuthorship W4386875129A5080106267 @default.
- W4386875129 hasBestOaLocation W43868751291 @default.
- W4386875129 hasConcept C119857082 @default.
- W4386875129 hasConcept C121332964 @default.
- W4386875129 hasConcept C124101348 @default.
- W4386875129 hasConcept C134306372 @default.
- W4386875129 hasConcept C154945302 @default.
- W4386875129 hasConcept C162324750 @default.
- W4386875129 hasConcept C187736073 @default.
- W4386875129 hasConcept C190470478 @default.
- W4386875129 hasConcept C197129107 @default.
- W4386875129 hasConcept C204321447 @default.
- W4386875129 hasConcept C23123220 @default.
- W4386875129 hasConcept C2780451532 @default.
- W4386875129 hasConcept C33923547 @default.
- W4386875129 hasConcept C36503486 @default.
- W4386875129 hasConcept C37914503 @default.
- W4386875129 hasConcept C41008148 @default.
- W4386875129 hasConcept C557471498 @default.
- W4386875129 hasConceptScore W4386875129C119857082 @default.
- W4386875129 hasConceptScore W4386875129C121332964 @default.
- W4386875129 hasConceptScore W4386875129C124101348 @default.
- W4386875129 hasConceptScore W4386875129C134306372 @default.
- W4386875129 hasConceptScore W4386875129C154945302 @default.
- W4386875129 hasConceptScore W4386875129C162324750 @default.
- W4386875129 hasConceptScore W4386875129C187736073 @default.
- W4386875129 hasConceptScore W4386875129C190470478 @default.
- W4386875129 hasConceptScore W4386875129C197129107 @default.
- W4386875129 hasConceptScore W4386875129C204321447 @default.
- W4386875129 hasConceptScore W4386875129C23123220 @default.
- W4386875129 hasConceptScore W4386875129C2780451532 @default.
- W4386875129 hasConceptScore W4386875129C33923547 @default.
- W4386875129 hasConceptScore W4386875129C36503486 @default.
- W4386875129 hasConceptScore W4386875129C37914503 @default.
- W4386875129 hasConceptScore W4386875129C41008148 @default.
- W4386875129 hasConceptScore W4386875129C557471498 @default.
- W4386875129 hasLocation W43868751291 @default.
- W4386875129 hasOpenAccess W4386875129 @default.
- W4386875129 hasPrimaryLocation W43868751291 @default.
- W4386875129 hasRelatedWork W2045871438 @default.
- W4386875129 hasRelatedWork W2122731942 @default.
- W4386875129 hasRelatedWork W2348159088 @default.
- W4386875129 hasRelatedWork W2350747448 @default.
- W4386875129 hasRelatedWork W2368095327 @default.
- W4386875129 hasRelatedWork W2369936857 @default.
- W4386875129 hasRelatedWork W2499363748 @default.
- W4386875129 hasRelatedWork W2743342830 @default.
- W4386875129 hasRelatedWork W2809363009 @default.
- W4386875129 hasRelatedWork W2968745142 @default.
- W4386875129 isParatext "false" @default.
- W4386875129 isRetracted "false" @default.
- W4386875129 workType "article" @default.