FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040731923> ?p ?o ?g. }

• W3040731923 endingPage "168" @default.
• W3040731923 startingPage "155" @default.
• W3040731923 abstract "Graph Convolutional Network (GCN) has experienced great success in graph analysis tasks. It works by smoothing the node features across the graph. The current GCN models overwhelmingly assume that the node feature information is complete. However, real-world graph data are often incomplete and containing missing features. Traditionally, people have to estimate and fill in the unknown features based on imputation techniques and then apply GCN. However, the process of feature filling and graph learning are separated, resulting in degraded and unstable performance. This problem becomes more serious when a large number of features are missing. We propose an approach that adapts GCN to graphs containing missing features. In contrast to traditional strategy, our approach integrates the processing of missing features and graph learning within the same neural network architecture. Our idea is to represent the missing data by Gaussian Mixture Model (GMM) and calculate the expected activation of neurons in the first hidden layer of GCN, while keeping the other layers of the network unchanged. This enables us to learn the GMM parameters and network weight parameters in an end-to-end manner. Notably, our approach does not increase the computational complexity of GCN and it is consistent with GCN when the features are complete. We demonstrate through extensive experiments that our approach significantly outperforms the imputation-based methods in node classification and link prediction tasks. We show that the performance of our approach for the case with a low level of missing features is even superior to GCN for the case with complete features." @default.
• W3040731923 created "2020-07-16" @default.
• W3040731923 creator A5003813798 @default.
• W3040731923 creator A5021687717 @default.
• W3040731923 creator A5076510932 @default.
• W3040731923 date "2021-04-01" @default.
• W3040731923 modified "2023-10-12" @default.
• W3040731923 title "Graph convolutional networks for graphs containing missing features" @default.
• W3040731923 cites W1992329416 @default.
• W3040731923 cites W2027731328 @default.
• W3040731923 cites W2054141820 @default.
• W3040731923 cites W2064186732 @default.
• W3040731923 cites W2094685358 @default.
• W3040731923 cites W2101491865 @default.
• W3040731923 cites W2116341502 @default.
• W3040731923 cites W2146332392 @default.
• W3040731923 cites W2153959628 @default.
• W3040731923 cites W2393319904 @default.
• W3040731923 cites W2606202972 @default.
• W3040731923 cites W2759136286 @default.
• W3040731923 cites W2788919350 @default.
• W3040731923 cites W2808409763 @default.
• W3040731923 cites W2906943923 @default.
• W3040731923 cites W2907373723 @default.
• W3040731923 cites W2908500813 @default.
• W3040731923 cites W2943501111 @default.
• W3040731923 cites W2945827377 @default.
• W3040731923 cites W2949208225 @default.
• W3040731923 cites W2949676527 @default.
• W3040731923 cites W2951626691 @default.
• W3040731923 cites W2962902912 @default.
• W3040731923 cites W2962975498 @default.
• W3040731923 cites W2963017945 @default.
• W3040731923 cites W2963653811 @default.
• W3040731923 cites W2964010366 @default.
• W3040731923 cites W2965819445 @default.
• W3040731923 cites W2966398094 @default.
• W3040731923 cites W2983010557 @default.
• W3040731923 cites W2997523134 @default.
• W3040731923 cites W3012593603 @default.
• W3040731923 cites W3042179685 @default.
• W3040731923 cites W3099825604 @default.
• W3040731923 cites W3100848837 @default.
• W3040731923 cites W3104097132 @default.
• W3040731923 cites W3105705953 @default.
• W3040731923 cites W3106390645 @default.
• W3040731923 cites W4291474301 @default.
• W3040731923 doi "https://doi.org/10.1016/j.future.2020.11.016" @default.
• W3040731923 hasPublicationYear "2021" @default.
• W3040731923 type Work @default.
• W3040731923 sameAs 3040731923 @default.
• W3040731923 citedByCount "32" @default.
• W3040731923 countsByYear W30407319232020 @default.
• W3040731923 countsByYear W30407319232021 @default.
• W3040731923 countsByYear W30407319232022 @default.
• W3040731923 countsByYear W30407319232023 @default.
• W3040731923 crossrefType "journal-article" @default.
• W3040731923 hasAuthorship W3040731923A5003813798 @default.
• W3040731923 hasAuthorship W3040731923A5021687717 @default.
• W3040731923 hasAuthorship W3040731923A5076510932 @default.
• W3040731923 hasBestOaLocation W30407319231 @default.
• W3040731923 hasConcept C11413529 @default.
• W3040731923 hasConcept C119857082 @default.
• W3040731923 hasConcept C124101348 @default.
• W3040731923 hasConcept C132525143 @default.
• W3040731923 hasConcept C153180895 @default.
• W3040731923 hasConcept C154945302 @default.
• W3040731923 hasConcept C31972630 @default.
• W3040731923 hasConcept C3770464 @default.
• W3040731923 hasConcept C41008148 @default.
• W3040731923 hasConcept C58041806 @default.
• W3040731923 hasConcept C80444323 @default.
• W3040731923 hasConcept C9357733 @default.
• W3040731923 hasConceptScore W3040731923C11413529 @default.
• W3040731923 hasConceptScore W3040731923C119857082 @default.
• W3040731923 hasConceptScore W3040731923C124101348 @default.
• W3040731923 hasConceptScore W3040731923C132525143 @default.
• W3040731923 hasConceptScore W3040731923C153180895 @default.
• W3040731923 hasConceptScore W3040731923C154945302 @default.
• W3040731923 hasConceptScore W3040731923C31972630 @default.
• W3040731923 hasConceptScore W3040731923C3770464 @default.
• W3040731923 hasConceptScore W3040731923C41008148 @default.
• W3040731923 hasConceptScore W3040731923C58041806 @default.
• W3040731923 hasConceptScore W3040731923C80444323 @default.
• W3040731923 hasConceptScore W3040731923C9357733 @default.
• W3040731923 hasFunder F4320321680 @default.
• W3040731923 hasFunder F4320334764 @default.
• W3040731923 hasFunder F4320334789 @default.
• W3040731923 hasLocation W30407319231 @default.
• W3040731923 hasLocation W30407319232 @default.
• W3040731923 hasLocation W30407319233 @default.
• W3040731923 hasOpenAccess W3040731923 @default.
• W3040731923 hasPrimaryLocation W30407319231 @default.
• W3040731923 hasRelatedWork W1574575415 @default.
• W3040731923 hasRelatedWork W2024529227 @default.
• W3040731923 hasRelatedWork W2081476516 @default.
• W3040731923 hasRelatedWork W2181530120 @default.
• W3040731923 hasRelatedWork W2581984549 @default.

• next