Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220742022> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4220742022 endingPage "79" @default.
- W4220742022 startingPage "70" @default.
- W4220742022 abstract "Graph classification aims to predict the property of the whole graph, which has attracted growing attention in the graph learning community. This problem has been extensively studied in the literature of both graph convolutional networks and graph kernels. Graph convolutional networks can learn effective node representations via message passing to mine graph topology in an implicit way, whereas graph kernels can explicitly utilize graph structural knowledge for classification. Due to the scarcity of labeled data in real-world applications, semi-supervised algorithms are anticipated for this problem. In this paper, we propose Graph Harmonic Neural Network (GHNN) which combines the advantages of both worlds to sufficiently leverage the unlabeled data, and thus overcomes label scarcity in semi-supervised scenarios. Specifically, our GHNN consists of a graph convolutional network (GCN) module and a graph kernel network (GKN) module that explore graph topology information from complementary perspectives. To fully leverage the unlabeled data, we develop a novel harmonic contrastive loss and a harmonic consistency loss to harmonize the training of two modules by giving priority to high-quality unlabeled data, thereby reconciling prediction consistency between both of them. In this manner, the two modules mutually enhance each other to sufficiently explore the graph topology of both labeled and unlabeled data. Extensive experiments on a variety of benchmarks demonstrate the effectiveness of our approach over competitive baselines." @default.
- W4220742022 created "2022-04-03" @default.
- W4220742022 creator A5018666299 @default.
- W4220742022 creator A5030001981 @default.
- W4220742022 creator A5059998187 @default.
- W4220742022 creator A5073859117 @default.
- W4220742022 creator A5080733133 @default.
- W4220742022 creator A5091013880 @default.
- W4220742022 date "2022-07-01" @default.
- W4220742022 modified "2023-10-16" @default.
- W4220742022 title "GHNN: Graph Harmonic Neural Networks for semi-supervised graph-level classification" @default.
- W4220742022 cites W1816257748 @default.
- W4220742022 cites W2092750499 @default.
- W4220742022 cites W2099438806 @default.
- W4220742022 cites W2159237780 @default.
- W4220742022 cites W2925177113 @default.
- W4220742022 cites W2964159205 @default.
- W4220742022 cites W3021294679 @default.
- W4220742022 cites W3030071125 @default.
- W4220742022 cites W3126769451 @default.
- W4220742022 cites W3141262995 @default.
- W4220742022 cites W4210257598 @default.
- W4220742022 doi "https://doi.org/10.1016/j.neunet.2022.03.018" @default.
- W4220742022 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35398673" @default.
- W4220742022 hasPublicationYear "2022" @default.
- W4220742022 type Work @default.
- W4220742022 citedByCount "17" @default.
- W4220742022 countsByYear W42207420222022 @default.
- W4220742022 countsByYear W42207420222023 @default.
- W4220742022 crossrefType "journal-article" @default.
- W4220742022 hasAuthorship W4220742022A5018666299 @default.
- W4220742022 hasAuthorship W4220742022A5030001981 @default.
- W4220742022 hasAuthorship W4220742022A5059998187 @default.
- W4220742022 hasAuthorship W4220742022A5073859117 @default.
- W4220742022 hasAuthorship W4220742022A5080733133 @default.
- W4220742022 hasAuthorship W4220742022A5091013880 @default.
- W4220742022 hasConcept C119857082 @default.
- W4220742022 hasConcept C132525143 @default.
- W4220742022 hasConcept C153083717 @default.
- W4220742022 hasConcept C154945302 @default.
- W4220742022 hasConcept C157406716 @default.
- W4220742022 hasConcept C203776342 @default.
- W4220742022 hasConcept C22149727 @default.
- W4220742022 hasConcept C41008148 @default.
- W4220742022 hasConcept C80444323 @default.
- W4220742022 hasConceptScore W4220742022C119857082 @default.
- W4220742022 hasConceptScore W4220742022C132525143 @default.
- W4220742022 hasConceptScore W4220742022C153083717 @default.
- W4220742022 hasConceptScore W4220742022C154945302 @default.
- W4220742022 hasConceptScore W4220742022C157406716 @default.
- W4220742022 hasConceptScore W4220742022C203776342 @default.
- W4220742022 hasConceptScore W4220742022C22149727 @default.
- W4220742022 hasConceptScore W4220742022C41008148 @default.
- W4220742022 hasConceptScore W4220742022C80444323 @default.
- W4220742022 hasFunder F4320321001 @default.
- W4220742022 hasFunder F4320321540 @default.
- W4220742022 hasLocation W42207420221 @default.
- W4220742022 hasLocation W42207420222 @default.
- W4220742022 hasOpenAccess W4220742022 @default.
- W4220742022 hasPrimaryLocation W42207420221 @default.
- W4220742022 hasRelatedWork W2961051133 @default.
- W4220742022 hasRelatedWork W3044158376 @default.
- W4220742022 hasRelatedWork W3051479560 @default.
- W4220742022 hasRelatedWork W3190313451 @default.
- W4220742022 hasRelatedWork W3208308319 @default.
- W4220742022 hasRelatedWork W3216189954 @default.
- W4220742022 hasRelatedWork W4225795456 @default.
- W4220742022 hasRelatedWork W4297895859 @default.
- W4220742022 hasRelatedWork W4306909306 @default.
- W4220742022 hasRelatedWork W4308164949 @default.
- W4220742022 hasVolume "151" @default.
- W4220742022 isParatext "false" @default.
- W4220742022 isRetracted "false" @default.
- W4220742022 workType "article" @default.