Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313476475> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4313476475 endingPage "11" @default.
- W4313476475 startingPage "1" @default.
- W4313476475 abstract "In biochemistry, graph structures have been widely used for modeling compounds, proteins, functional interactions, etc. A common task that divides these graphs into different categories, known as graph classification, highly relies on the quality of the representations of graphs. With the advance in graph neural networks, message-passing-based methods are adopted to iteratively aggregate neighborhood information for better graph representations. These methods, though powerful, still suffer from some shortcomings. The first challenge is that pooling-based methods in graph neural networks may sometimes ignore the part-whole hierarchies naturally existing in graph structures. These part-whole relationships are usually valuable for many molecular function prediction tasks. The second challenge is that most existing methods do not take the heterogeneity embedded in graph representations into consideration. Disentangling the heterogeneity will increase the performance and interpretability of models. This paper proposes a graph capsule network for graph classification tasks with disentangled feature representations learned automatically by well-designed algorithms. This method is capable of, on the one hand, decomposing heterogeneous representations to more fine-grained elements, whilst on the other hand, capturing part-whole relationships using capsules. Extensive experiments performed on several public-available biochemistry datasets demonstrated the effectiveness of the proposed method, compared with nine state-of-the-art graph learning methods." @default.
- W4313476475 created "2023-01-06" @default.
- W4313476475 creator A5014482509 @default.
- W4313476475 creator A5021000274 @default.
- W4313476475 creator A5048050496 @default.
- W4313476475 creator A5051706630 @default.
- W4313476475 creator A5054603875 @default.
- W4313476475 date "2023-01-01" @default.
- W4313476475 modified "2023-09-26" @default.
- W4313476475 title "Hierarchical Graph Capsule Networks for Molecular Function Classification with Disentangled Representations" @default.
- W4313476475 doi "https://doi.org/10.1109/tcbb.2022.3233354" @default.
- W4313476475 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37018300" @default.
- W4313476475 hasPublicationYear "2023" @default.
- W4313476475 type Work @default.
- W4313476475 citedByCount "0" @default.
- W4313476475 crossrefType "journal-article" @default.
- W4313476475 hasAuthorship W4313476475A5014482509 @default.
- W4313476475 hasAuthorship W4313476475A5021000274 @default.
- W4313476475 hasAuthorship W4313476475A5048050496 @default.
- W4313476475 hasAuthorship W4313476475A5051706630 @default.
- W4313476475 hasAuthorship W4313476475A5054603875 @default.
- W4313476475 hasConcept C106937863 @default.
- W4313476475 hasConcept C119857082 @default.
- W4313476475 hasConcept C132525143 @default.
- W4313476475 hasConcept C154945302 @default.
- W4313476475 hasConcept C2781067378 @default.
- W4313476475 hasConcept C41008148 @default.
- W4313476475 hasConcept C70437156 @default.
- W4313476475 hasConcept C80444323 @default.
- W4313476475 hasConceptScore W4313476475C106937863 @default.
- W4313476475 hasConceptScore W4313476475C119857082 @default.
- W4313476475 hasConceptScore W4313476475C132525143 @default.
- W4313476475 hasConceptScore W4313476475C154945302 @default.
- W4313476475 hasConceptScore W4313476475C2781067378 @default.
- W4313476475 hasConceptScore W4313476475C41008148 @default.
- W4313476475 hasConceptScore W4313476475C70437156 @default.
- W4313476475 hasConceptScore W4313476475C80444323 @default.
- W4313476475 hasLocation W43134764751 @default.
- W4313476475 hasLocation W43134764752 @default.
- W4313476475 hasOpenAccess W4313476475 @default.
- W4313476475 hasPrimaryLocation W43134764751 @default.
- W4313476475 hasRelatedWork W3006943036 @default.
- W4313476475 hasRelatedWork W3093454656 @default.
- W4313476475 hasRelatedWork W4200511449 @default.
- W4313476475 hasRelatedWork W4206534706 @default.
- W4313476475 hasRelatedWork W4229079080 @default.
- W4313476475 hasRelatedWork W4299487748 @default.
- W4313476475 hasRelatedWork W4319294264 @default.
- W4313476475 hasRelatedWork W4385957992 @default.
- W4313476475 hasRelatedWork W4385965371 @default.
- W4313476475 hasRelatedWork W4386025632 @default.
- W4313476475 isParatext "false" @default.
- W4313476475 isRetracted "false" @default.
- W4313476475 workType "article" @default.