Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210516846> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3210516846 abstract "Reorganizing implicit feedback of users as a user-item interaction graph facilitates the applications of graph convolutional networks (GCNs) in recommendation tasks. In the interaction graph, edges between user and item nodes function as the main element of GCNs to perform information propagation and generate informative representations. Nevertheless, an underlying challenge lies in the quality of interaction graph, since observed interactions with less-interested items occur in implicit feedback (say, a user views micro-videos accidentally). This means that the neighborhoods involved with such false-positive edges will be influenced negatively and the signal on user preference can be severely contaminated. However, existing GCN-based recommender models leave such challenge under-explored, resulting in suboptimal representations and performance. In this work, we focus on adaptively refining the structure of interaction graph to discover and prune potential false-positive edges. Towards this end, we devise a new GCN-based recommender model, emph{Graph-Refined Convolutional Network} (GRCN), which adjusts the structure of interaction graph adaptively based on status of model training, instead of remaining the fixed structure. In particular, a graph refining layer is designed to identify the noisy edges with the high confidence of being false-positive interactions, and consequently prune them in a soft manner. We then apply a graph convolutional layer on the refined graph to distill informative signals on user preference. Through extensive experiments on three datasets for micro-video recommendation, we validate the rationality and effectiveness of our GRCN. Further in-depth analysis presents how the refined graph benefits the GCN-based recommender model." @default.
- W3210516846 created "2021-11-08" @default.
- W3210516846 creator A5038612499 @default.
- W3210516846 creator A5038668215 @default.
- W3210516846 creator A5039731055 @default.
- W3210516846 creator A5048845021 @default.
- W3210516846 creator A5089404640 @default.
- W3210516846 date "2021-11-03" @default.
- W3210516846 modified "2023-09-24" @default.
- W3210516846 title "GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback" @default.
- W3210516846 cites W1533861849 @default.
- W3210516846 cites W1665214252 @default.
- W3210516846 cites W2101409192 @default.
- W3210516846 cites W2140310134 @default.
- W3210516846 cites W2194775991 @default.
- W3210516846 cites W2340502990 @default.
- W3210516846 cites W2519887557 @default.
- W3210516846 cites W2526050071 @default.
- W3210516846 cites W2601450892 @default.
- W3210516846 cites W2624407581 @default.
- W3210516846 cites W2624431344 @default.
- W3210516846 cites W2725606191 @default.
- W3210516846 cites W2741249238 @default.
- W3210516846 cites W2752172973 @default.
- W3210516846 cites W2765757915 @default.
- W3210516846 cites W2766187676 @default.
- W3210516846 cites W2894039884 @default.
- W3210516846 cites W2897298014 @default.
- W3210516846 cites W2945420892 @default.
- W3210516846 cites W2945623882 @default.
- W3210516846 cites W2949208225 @default.
- W3210516846 cites W2956959730 @default.
- W3210516846 cites W2962767366 @default.
- W3210516846 cites W2963655167 @default.
- W3210516846 cites W2963858333 @default.
- W3210516846 cites W2964121744 @default.
- W3210516846 cites W2969960436 @default.
- W3210516846 cites W2981384185 @default.
- W3210516846 cites W2981525000 @default.
- W3210516846 cites W2981569692 @default.
- W3210516846 cites W2982108874 @default.
- W3210516846 cites W2989619960 @default.
- W3210516846 cites W2997404190 @default.
- W3210516846 cites W3024534448 @default.
- W3210516846 cites W3045108742 @default.
- W3210516846 cites W3093242741 @default.
- W3210516846 cites W3095972335 @default.
- W3210516846 cites W3100278010 @default.
- W3210516846 cites W3100324210 @default.
- W3210516846 cites W3100848837 @default.
- W3210516846 cites W3106302634 @default.
- W3210516846 cites W3106445281 @default.
- W3210516846 doi "https://doi.org/10.48550/arxiv.2111.02036" @default.
- W3210516846 hasPublicationYear "2021" @default.
- W3210516846 type Work @default.
- W3210516846 sameAs 3210516846 @default.
- W3210516846 citedByCount "0" @default.
- W3210516846 crossrefType "posted-content" @default.
- W3210516846 hasAuthorship W3210516846A5038612499 @default.
- W3210516846 hasAuthorship W3210516846A5038668215 @default.
- W3210516846 hasAuthorship W3210516846A5039731055 @default.
- W3210516846 hasAuthorship W3210516846A5048845021 @default.
- W3210516846 hasAuthorship W3210516846A5089404640 @default.
- W3210516846 hasBestOaLocation W32105168461 @default.
- W3210516846 hasConcept C119857082 @default.
- W3210516846 hasConcept C124101348 @default.
- W3210516846 hasConcept C132525143 @default.
- W3210516846 hasConcept C154945302 @default.
- W3210516846 hasConcept C23123220 @default.
- W3210516846 hasConcept C41008148 @default.
- W3210516846 hasConcept C557471498 @default.
- W3210516846 hasConcept C80444323 @default.
- W3210516846 hasConceptScore W3210516846C119857082 @default.
- W3210516846 hasConceptScore W3210516846C124101348 @default.
- W3210516846 hasConceptScore W3210516846C132525143 @default.
- W3210516846 hasConceptScore W3210516846C154945302 @default.
- W3210516846 hasConceptScore W3210516846C23123220 @default.
- W3210516846 hasConceptScore W3210516846C41008148 @default.
- W3210516846 hasConceptScore W3210516846C557471498 @default.
- W3210516846 hasConceptScore W3210516846C80444323 @default.
- W3210516846 hasLocation W32105168461 @default.
- W3210516846 hasLocation W32105168462 @default.
- W3210516846 hasOpenAccess W3210516846 @default.
- W3210516846 hasPrimaryLocation W32105168461 @default.
- W3210516846 hasRelatedWork W2002418671 @default.
- W3210516846 hasRelatedWork W2045871438 @default.
- W3210516846 hasRelatedWork W2122731942 @default.
- W3210516846 hasRelatedWork W2348159088 @default.
- W3210516846 hasRelatedWork W2350747448 @default.
- W3210516846 hasRelatedWork W2368095327 @default.
- W3210516846 hasRelatedWork W2402445420 @default.
- W3210516846 hasRelatedWork W2514849893 @default.
- W3210516846 hasRelatedWork W2809363009 @default.
- W3210516846 hasRelatedWork W2968745142 @default.
- W3210516846 isParatext "false" @default.
- W3210516846 isRetracted "false" @default.
- W3210516846 magId "3210516846" @default.
- W3210516846 workType "article" @default.