FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380758439> ?p ?o ?g. }

• W4380758439 endingPage "110523" @default.
• W4380758439 startingPage "110523" @default.
• W4380758439 abstract "Multi-behavior recommendation (MBR) aims to improve the prediction of the target behavior (i.e., purchase) by exploiting multi-typed auxiliary behaviors, such as page view, cart and favorite. Recently, leveraging Graph Neural Networks (GNNs) to capture collaborative signals has been the mainstream paradigm for MBR. However, GNN-based MBR suffers from data sparsity in real-world scenarios and thus performs mediocrely. Excitingly, contrastive learning which can mine additional self-supervised signals from raw data, holds great potential to alleviate this problem. Naturally, we seek to exploit contrastive learning to enhance MBR, while two key challenges have yet to be addressed: (i) Difficult to learn reliable representations under different behaviors; (ii) Sparse supervised signals under target behavior. To tackle the above challenges, in this paper, we propose a novel Dual-Scale Contrastive Learning (DSCL) framework. Unlike traditional contrastive learning methods that artificially construct two views through data augmentation, we comprehensively consider two different views for MBR, including the collaborative view and the semantic view. Specifically, we regard the user–item graph as a collaborative view and the user–user graph as a semantic view. In particular, we develop two novel contrastive learning objectives at two scales. For the first challenge, we devise local-to-context contrastive learning within behaviors on collaborative view, which enhances the representation learning by incorporating potential neighbors into the contrastive learning from the graph topological space and the semantic space, respectively. As for the second challenge, we design local-to-local contrastive learning across behaviors on a semantic view, which has the benefit of capturing commonalities between different behaviors and integrating them into the target behavior to alleviate the sparse supervised signal problem of the target behavior. In addition, we also propose an adaptive weight network to efficiently customize the integration of all losses. Extensive experiments on three real-world benchmark datasets show that our proposed DSCL is significantly superior to various state-of-the-art recommendation methods." @default.
• W4380758439 created "2023-06-16" @default.
• W4380758439 creator A5006218539 @default.
• W4380758439 creator A5021874629 @default.
• W4380758439 creator A5049801163 @default.
• W4380758439 creator A5053794277 @default.
• W4380758439 creator A5080228341 @default.
• W4380758439 date "2023-09-01" @default.
• W4380758439 modified "2023-10-04" @default.
• W4380758439 title "Dual-scale Contrastive Learning for multi-behavior recommendation" @default.
• W4380758439 cites W1985554184 @default.
• W4380758439 cites W3097300053 @default.
• W4380758439 cites W3100592176 @default.
• W4380758439 doi "https://doi.org/10.1016/j.asoc.2023.110523" @default.
• W4380758439 hasPublicationYear "2023" @default.
• W4380758439 type Work @default.
• W4380758439 citedByCount "0" @default.
• W4380758439 crossrefType "journal-article" @default.
• W4380758439 hasAuthorship W4380758439A5006218539 @default.
• W4380758439 hasAuthorship W4380758439A5021874629 @default.
• W4380758439 hasAuthorship W4380758439A5049801163 @default.
• W4380758439 hasAuthorship W4380758439A5053794277 @default.
• W4380758439 hasAuthorship W4380758439A5080228341 @default.
• W4380758439 hasConcept C119857082 @default.
• W4380758439 hasConcept C132525143 @default.
• W4380758439 hasConcept C154945302 @default.
• W4380758439 hasConcept C165696696 @default.
• W4380758439 hasConcept C204321447 @default.
• W4380758439 hasConcept C38652104 @default.
• W4380758439 hasConcept C41008148 @default.
• W4380758439 hasConcept C59404180 @default.
• W4380758439 hasConcept C80444323 @default.
• W4380758439 hasConceptScore W4380758439C119857082 @default.
• W4380758439 hasConceptScore W4380758439C132525143 @default.
• W4380758439 hasConceptScore W4380758439C154945302 @default.
• W4380758439 hasConceptScore W4380758439C165696696 @default.
• W4380758439 hasConceptScore W4380758439C204321447 @default.
• W4380758439 hasConceptScore W4380758439C38652104 @default.
• W4380758439 hasConceptScore W4380758439C41008148 @default.
• W4380758439 hasConceptScore W4380758439C59404180 @default.
• W4380758439 hasConceptScore W4380758439C80444323 @default.
• W4380758439 hasLocation W43807584391 @default.
• W4380758439 hasOpenAccess W4380758439 @default.
• W4380758439 hasPrimaryLocation W43807584391 @default.
• W4380758439 hasRelatedWork W1607315280 @default.
• W4380758439 hasRelatedWork W2331043530 @default.
• W4380758439 hasRelatedWork W2374725260 @default.
• W4380758439 hasRelatedWork W2393933887 @default.
• W4380758439 hasRelatedWork W2891961174 @default.
• W4380758439 hasRelatedWork W2961085424 @default.
• W4380758439 hasRelatedWork W2997512100 @default.
• W4380758439 hasRelatedWork W3087493185 @default.
• W4380758439 hasRelatedWork W4206762304 @default.
• W4380758439 hasRelatedWork W4306674287 @default.
• W4380758439 hasVolume "144" @default.
• W4380758439 isParatext "false" @default.
• W4380758439 isRetracted "false" @default.
• W4380758439 workType "article" @default.