Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287119897> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4287119897 abstract "Making accurate recommendations for cold-start users has been a longstanding and critical challenge for recommender systems (RS). Cross-domain recommendations (CDR) offer a solution to tackle such a cold-start problem when there is no sufficient data for the users who have rarely used the system. An effective approach in CDR is to leverage the knowledge (e.g., user representations) learned from a related but different domain and transfer it to the target domain. Fine-tuning works as an effective transfer learning technique for this objective, which adapts the parameters of a pre-trained model from the source domain to the target domain. However, current methods are mainly based on the global fine-tuning strategy: the decision of which layers of the pre-trained model to freeze or fine-tune is taken for all users in the target domain. In this paper, we argue that users in RS are personalized and should have their own fine-tuning policies for better preference transfer learning. As such, we propose a novel User-specific Adaptive Fine-tuning method (UAF), selecting which layers of the pre-trained network to fine-tune, on a per-user basis. Specifically, we devise a policy network with three alternative strategies to automatically decide which layers to be fine-tuned and which layers to have their parameters frozen for each user. Extensive experiments show that the proposed UAF exhibits significantly better and more robust performance for user cold-start recommendation." @default.
- W4287119897 created "2022-07-25" @default.
- W4287119897 creator A5010738468 @default.
- W4287119897 creator A5038668215 @default.
- W4287119897 creator A5046405692 @default.
- W4287119897 creator A5059967200 @default.
- W4287119897 creator A5067142424 @default.
- W4287119897 creator A5081665927 @default.
- W4287119897 date "2021-06-14" @default.
- W4287119897 modified "2023-09-24" @default.
- W4287119897 title "User-specific Adaptive Fine-tuning for Cross-domain Recommendations" @default.
- W4287119897 hasPublicationYear "2021" @default.
- W4287119897 type Work @default.
- W4287119897 citedByCount "0" @default.
- W4287119897 crossrefType "posted-content" @default.
- W4287119897 hasAuthorship W4287119897A5010738468 @default.
- W4287119897 hasAuthorship W4287119897A5038668215 @default.
- W4287119897 hasAuthorship W4287119897A5046405692 @default.
- W4287119897 hasAuthorship W4287119897A5059967200 @default.
- W4287119897 hasAuthorship W4287119897A5067142424 @default.
- W4287119897 hasAuthorship W4287119897A5081665927 @default.
- W4287119897 hasBestOaLocation W42871198971 @default.
- W4287119897 hasConcept C107457646 @default.
- W4287119897 hasConcept C119857082 @default.
- W4287119897 hasConcept C121332964 @default.
- W4287119897 hasConcept C127413603 @default.
- W4287119897 hasConcept C134306372 @default.
- W4287119897 hasConcept C146978453 @default.
- W4287119897 hasConcept C150899416 @default.
- W4287119897 hasConcept C153083717 @default.
- W4287119897 hasConcept C154945302 @default.
- W4287119897 hasConcept C157524613 @default.
- W4287119897 hasConcept C162324750 @default.
- W4287119897 hasConcept C175444787 @default.
- W4287119897 hasConcept C21569690 @default.
- W4287119897 hasConcept C2778956030 @default.
- W4287119897 hasConcept C2781249084 @default.
- W4287119897 hasConcept C33923547 @default.
- W4287119897 hasConcept C36503486 @default.
- W4287119897 hasConcept C41008148 @default.
- W4287119897 hasConcept C557471498 @default.
- W4287119897 hasConcept C62520636 @default.
- W4287119897 hasConceptScore W4287119897C107457646 @default.
- W4287119897 hasConceptScore W4287119897C119857082 @default.
- W4287119897 hasConceptScore W4287119897C121332964 @default.
- W4287119897 hasConceptScore W4287119897C127413603 @default.
- W4287119897 hasConceptScore W4287119897C134306372 @default.
- W4287119897 hasConceptScore W4287119897C146978453 @default.
- W4287119897 hasConceptScore W4287119897C150899416 @default.
- W4287119897 hasConceptScore W4287119897C153083717 @default.
- W4287119897 hasConceptScore W4287119897C154945302 @default.
- W4287119897 hasConceptScore W4287119897C157524613 @default.
- W4287119897 hasConceptScore W4287119897C162324750 @default.
- W4287119897 hasConceptScore W4287119897C175444787 @default.
- W4287119897 hasConceptScore W4287119897C21569690 @default.
- W4287119897 hasConceptScore W4287119897C2778956030 @default.
- W4287119897 hasConceptScore W4287119897C2781249084 @default.
- W4287119897 hasConceptScore W4287119897C33923547 @default.
- W4287119897 hasConceptScore W4287119897C36503486 @default.
- W4287119897 hasConceptScore W4287119897C41008148 @default.
- W4287119897 hasConceptScore W4287119897C557471498 @default.
- W4287119897 hasConceptScore W4287119897C62520636 @default.
- W4287119897 hasLocation W42871198971 @default.
- W4287119897 hasOpenAccess W4287119897 @default.
- W4287119897 hasPrimaryLocation W42871198971 @default.
- W4287119897 hasRelatedWork W10944326 @default.
- W4287119897 hasRelatedWork W11484169 @default.
- W4287119897 hasRelatedWork W12032051 @default.
- W4287119897 hasRelatedWork W12165144 @default.
- W4287119897 hasRelatedWork W12560049 @default.
- W4287119897 hasRelatedWork W1721622 @default.
- W4287119897 hasRelatedWork W6362254 @default.
- W4287119897 hasRelatedWork W7314787 @default.
- W4287119897 hasRelatedWork W8474372 @default.
- W4287119897 hasRelatedWork W9977724 @default.
- W4287119897 isParatext "false" @default.
- W4287119897 isRetracted "false" @default.
- W4287119897 workType "article" @default.