FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3155496675> ?p ?o ?g. }

• W3155496675 abstract "Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complex and user relations can be high-order. Hypergraph provides a natural way to model high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. Extensive experiments on multiple real-world datasets demonstrate the superiority of the proposed model over the current SOTA methods, and the ablation study verifies the effectiveness and rationale of the multi-channel setting and the self-supervised task. The implementation of our model is available via https://github.com/Coder-Yu/RecQ." @default.
• W3155496675 created "2021-04-26" @default.
• W3155496675 creator A5000755750 @default.
• W3155496675 creator A5005504607 @default.
• W3155496675 creator A5029588473 @default.
• W3155496675 creator A5065191560 @default.
• W3155496675 creator A5084564297 @default.
• W3155496675 creator A5088492734 @default.
• W3155496675 date "2021-04-19" @default.
• W3155496675 modified "2023-10-17" @default.
• W3155496675 title "Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation" @default.
• W3155496675 cites W1840106123 @default.
• W3155496675 cites W1980127182 @default.
• W3155496675 cites W1991055526 @default.
• W3155496675 cites W2093219534 @default.
• W3155496675 cites W2096563449 @default.
• W3155496675 cites W2112008792 @default.
• W3155496675 cites W2119825970 @default.
• W3155496675 cites W2130354913 @default.
• W3155496675 cites W2144487656 @default.
• W3155496675 cites W2244405900 @default.
• W3155496675 cites W2438985978 @default.
• W3155496675 cites W2444485119 @default.
• W3155496675 cites W2509678028 @default.
• W3155496675 cites W2587290924 @default.
• W3155496675 cites W2756072049 @default.
• W3155496675 cites W2787879486 @default.
• W3155496675 cites W2795104036 @default.
• W3155496675 cites W2892880750 @default.
• W3155496675 cites W2896367309 @default.
• W3155496675 cites W2908404712 @default.
• W3155496675 cites W2913696439 @default.
• W3155496675 cites W2914721378 @default.
• W3155496675 cites W2951217911 @default.
• W3155496675 cites W2951431594 @default.
• W3155496675 cites W2981952041 @default.
• W3155496675 cites W2998431760 @default.
• W3155496675 cites W3012816161 @default.
• W3155496675 cites W3025937945 @default.
• W3155496675 cites W3034853385 @default.
• W3155496675 cites W3035666843 @default.
• W3155496675 cites W3035748723 @default.
• W3155496675 cites W3045200674 @default.
• W3155496675 cites W3080374445 @default.
• W3155496675 cites W3080566854 @default.
• W3155496675 cites W3084515140 @default.
• W3155496675 cites W3099152386 @default.
• W3155496675 cites W3099602291 @default.
• W3155496675 cites W3099939189 @default.
• W3155496675 cites W3100260481 @default.
• W3155496675 cites W3104326162 @default.
• W3155496675 cites W4206255050 @default.
• W3155496675 cites W4210257598 @default.
• W3155496675 cites W3127813352 @default.
• W3155496675 doi "https://doi.org/10.1145/3442381.3449844" @default.
• W3155496675 hasPublicationYear "2021" @default.
• W3155496675 type Work @default.
• W3155496675 sameAs 3155496675 @default.
• W3155496675 citedByCount "119" @default.
• W3155496675 countsByYear W31554966752021 @default.
• W3155496675 countsByYear W31554966752022 @default.
• W3155496675 countsByYear W31554966752023 @default.
• W3155496675 crossrefType "proceedings-article" @default.
• W3155496675 hasAuthorship W3155496675A5000755750 @default.
• W3155496675 hasAuthorship W3155496675A5005504607 @default.
• W3155496675 hasAuthorship W3155496675A5029588473 @default.
• W3155496675 hasAuthorship W3155496675A5065191560 @default.
• W3155496675 hasAuthorship W3155496675A5084564297 @default.
• W3155496675 hasAuthorship W3155496675A5088492734 @default.
• W3155496675 hasBestOaLocation W31554966752 @default.
• W3155496675 hasConcept C10138342 @default.
• W3155496675 hasConcept C118615104 @default.
• W3155496675 hasConcept C119857082 @default.
• W3155496675 hasConcept C124101348 @default.
• W3155496675 hasConcept C127162648 @default.
• W3155496675 hasConcept C136764020 @default.
• W3155496675 hasConcept C154945302 @default.
• W3155496675 hasConcept C162324750 @default.
• W3155496675 hasConcept C165696696 @default.
• W3155496675 hasConcept C182306322 @default.
• W3155496675 hasConcept C184898388 @default.
• W3155496675 hasConcept C187736073 @default.
• W3155496675 hasConcept C23123220 @default.
• W3155496675 hasConcept C25343380 @default.
• W3155496675 hasConcept C2780451532 @default.
• W3155496675 hasConcept C2781221856 @default.
• W3155496675 hasConcept C31258907 @default.
• W3155496675 hasConcept C33923547 @default.
• W3155496675 hasConcept C38652104 @default.
• W3155496675 hasConcept C41008148 @default.
• W3155496675 hasConcept C4727928 @default.
• W3155496675 hasConcept C518677369 @default.
• W3155496675 hasConcept C557471498 @default.
• W3155496675 hasConcept C80444323 @default.
• W3155496675 hasConceptScore W3155496675C10138342 @default.
• W3155496675 hasConceptScore W3155496675C118615104 @default.
• W3155496675 hasConceptScore W3155496675C119857082 @default.
• W3155496675 hasConceptScore W3155496675C124101348 @default.
• W3155496675 hasConceptScore W3155496675C127162648 @default.
• W3155496675 hasConceptScore W3155496675C136764020 @default.

• next