FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385270185> ?p ?o ?g. }

• W4385270185 abstract "To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations. Many state-of-the-art (SOTA) methods fuse different sources of information (user, item, knowledge graph, tags, etc.) into a graph and use Graph Neural Networks (GNNs) to introduce the auxiliary information through the message passing paradigm. In this work, we seek an alternative framework that is light and effective through self-supervised learning across different sources of information, particularly for the commonly accessible item tag information. We use a self-supervision signal to pair users with the auxiliary information (tags) associated with the items they have interacted with before. To achieve the pairing, we create a proxy training task. For a given item, the model predicts which is the correct pairing between the representations obtained from the users that have interacted with this item and the tags assigned to it. This design provides an efficient solution, using the auxiliary information directly to enhance the quality of user and item embeddings. User behavior in recommendation systems is driven by the complex interactions of many factors behind the users’ decision-making processes. To make the pairing process more fine-grained and avoid embedding collapse, we propose a user intent-aware self-supervised pairing process where we split the user embeddings into multiple sub-embedding vectors. Each sub-embedding vector captures a specific user intent via self-supervised alignment with a particular cluster of tags. We integrate our designed framework with various recommendation models, demonstrating its flexibility and compatibility. Through comparison with numerous SOTA methods on seven real-world datasets, we show that our method can achieve better performance while requiring less training time. This indicates the potential of applying our approach on web-scale datasets." @default.
• W4385270185 created "2023-07-27" @default.
• W4385270185 creator A5009031715 @default.
• W4385270185 creator A5017643618 @default.
• W4385270185 creator A5028155508 @default.
• W4385270185 creator A5054330014 @default.
• W4385270185 creator A5061195656 @default.
• W4385270185 creator A5074277827 @default.
• W4385270185 creator A5087083916 @default.
• W4385270185 date "2023-04-01" @default.
• W4385270185 modified "2023-09-24" @default.
• W4385270185 title "Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation" @default.
• W4385270185 cites W2010187764 @default.
• W4385270185 cites W2018426558 @default.
• W4385270185 cites W2054141820 @default.
• W4385270185 cites W2069870183 @default.
• W4385270185 cites W2150593711 @default.
• W4385270185 cites W2184957013 @default.
• W4385270185 cites W2295739661 @default.
• W4385270185 cites W2308529009 @default.
• W4385270185 cites W2315503695 @default.
• W4385270185 cites W2507427036 @default.
• W4385270185 cites W2509893387 @default.
• W4385270185 cites W2605350416 @default.
• W4385270185 cites W2618756248 @default.
• W4385270185 cites W2884134047 @default.
• W4385270185 cites W2891328459 @default.
• W4385270185 cites W2945623882 @default.
• W4385270185 cites W2962992837 @default.
• W4385270185 cites W2963869731 @default.
• W4385270185 cites W2964732194 @default.
• W4385270185 cites W3003372423 @default.
• W4385270185 cites W3033630125 @default.
• W4385270185 cites W3034357141 @default.
• W4385270185 cites W3035524453 @default.
• W4385270185 cites W3045200674 @default.
• W4385270185 cites W3093570486 @default.
• W4385270185 cites W3098087397 @default.
• W4385270185 cites W3100260481 @default.
• W4385270185 cites W3100324210 @default.
• W4385270185 cites W3101709902 @default.
• W4385270185 cites W3103362336 @default.
• W4385270185 cites W3106439716 @default.
• W4385270185 cites W3129482887 @default.
• W4385270185 cites W3154394390 @default.
• W4385270185 cites W3155496675 @default.
• W4385270185 cites W3171007011 @default.
• W4385270185 cites W3207257408 @default.
• W4385270185 cites W3208338073 @default.
• W4385270185 cites W4225412853 @default.
• W4385270185 cites W4297971002 @default.
• W4385270185 doi "https://doi.org/10.1109/icde55515.2023.00090" @default.
• W4385270185 hasPublicationYear "2023" @default.
• W4385270185 type Work @default.
• W4385270185 citedByCount "0" @default.
• W4385270185 crossrefType "proceedings-article" @default.
• W4385270185 hasAuthorship W4385270185A5009031715 @default.
• W4385270185 hasAuthorship W4385270185A5017643618 @default.
• W4385270185 hasAuthorship W4385270185A5028155508 @default.
• W4385270185 hasAuthorship W4385270185A5054330014 @default.
• W4385270185 hasAuthorship W4385270185A5061195656 @default.
• W4385270185 hasAuthorship W4385270185A5074277827 @default.
• W4385270185 hasAuthorship W4385270185A5087083916 @default.
• W4385270185 hasBestOaLocation W43852701852 @default.
• W4385270185 hasConcept C107457646 @default.
• W4385270185 hasConcept C111919701 @default.
• W4385270185 hasConcept C119857082 @default.
• W4385270185 hasConcept C121332964 @default.
• W4385270185 hasConcept C132525143 @default.
• W4385270185 hasConcept C14103023 @default.
• W4385270185 hasConcept C154945302 @default.
• W4385270185 hasConcept C23123220 @default.
• W4385270185 hasConcept C41008148 @default.
• W4385270185 hasConcept C41608201 @default.
• W4385270185 hasConcept C54101563 @default.
• W4385270185 hasConcept C557471498 @default.
• W4385270185 hasConcept C62520636 @default.
• W4385270185 hasConcept C75564084 @default.
• W4385270185 hasConcept C80444323 @default.
• W4385270185 hasConcept C98045186 @default.
• W4385270185 hasConceptScore W4385270185C107457646 @default.
• W4385270185 hasConceptScore W4385270185C111919701 @default.
• W4385270185 hasConceptScore W4385270185C119857082 @default.
• W4385270185 hasConceptScore W4385270185C121332964 @default.
• W4385270185 hasConceptScore W4385270185C132525143 @default.
• W4385270185 hasConceptScore W4385270185C14103023 @default.
• W4385270185 hasConceptScore W4385270185C154945302 @default.
• W4385270185 hasConceptScore W4385270185C23123220 @default.
• W4385270185 hasConceptScore W4385270185C41008148 @default.
• W4385270185 hasConceptScore W4385270185C41608201 @default.
• W4385270185 hasConceptScore W4385270185C54101563 @default.
• W4385270185 hasConceptScore W4385270185C557471498 @default.
• W4385270185 hasConceptScore W4385270185C62520636 @default.
• W4385270185 hasConceptScore W4385270185C75564084 @default.
• W4385270185 hasConceptScore W4385270185C80444323 @default.
• W4385270185 hasConceptScore W4385270185C98045186 @default.
• W4385270185 hasLocation W43852701851 @default.
• W4385270185 hasLocation W43852701852 @default.
• W4385270185 hasOpenAccess W4385270185 @default.
• W4385270185 hasPrimaryLocation W43852701851 @default.

• next