Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947030669> ?p ?o ?g. }
- W2947030669 abstract "Recent work in graph neural networks (GNNs) has led to improvements in molecular activity and property prediction tasks. Unfortunately, GNNs often fail to capture the relative importance of interactions between molecular substructures, in part due to the absence of efficient intermediate pooling steps. To address these issues, we propose LaPool (Laplacian Pooling), a novel, data-driven, and interpretable hierarchical graph pooling method that takes into account both node features and graph structure to improve molecular representation. We benchmark LaPool on molecular graph prediction and understanding tasks and show that it outperforms recent GNNs. Interestingly, LaPool also remains competitive on non-molecular tasks. Both quantitative and qualitative assessments are done to demonstrate LaPool's improved interpretability and highlight its potential benefits in drug design. Finally, we demonstrate LaPool's utility for the generation of valid and novel molecules by incorporating it into an adversarial autoencoder." @default.
- W2947030669 created "2019-06-07" @default.
- W2947030669 creator A5012750505 @default.
- W2947030669 creator A5037753193 @default.
- W2947030669 creator A5061067204 @default.
- W2947030669 creator A5064214996 @default.
- W2947030669 date "2019-05-28" @default.
- W2947030669 modified "2023-09-27" @default.
- W2947030669 title "Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling." @default.
- W2947030669 cites W1522301498 @default.
- W2947030669 cites W1988037271 @default.
- W2947030669 cites W2033777798 @default.
- W2947030669 cites W2041473955 @default.
- W2947030669 cites W2079257299 @default.
- W2947030669 cites W2080635178 @default.
- W2947030669 cites W2132914434 @default.
- W2947030669 cites W2136316075 @default.
- W2947030669 cites W2161763921 @default.
- W2947030669 cites W2198726572 @default.
- W2947030669 cites W2244807774 @default.
- W2947030669 cites W2253795368 @default.
- W2947030669 cites W2405035126 @default.
- W2947030669 cites W2594183968 @default.
- W2947030669 cites W2594633041 @default.
- W2947030669 cites W2624431344 @default.
- W2947030669 cites W2736137960 @default.
- W2947030669 cites W2767757834 @default.
- W2947030669 cites W2786103815 @default.
- W2947030669 cites W2786722833 @default.
- W2947030669 cites W2788919350 @default.
- W2947030669 cites W2805177834 @default.
- W2947030669 cites W2806351858 @default.
- W2947030669 cites W2811124557 @default.
- W2947030669 cites W2894175828 @default.
- W2947030669 cites W2901454299 @default.
- W2947030669 cites W2903425689 @default.
- W2947030669 cites W2942587884 @default.
- W2947030669 cites W2949945331 @default.
- W2947030669 cites W2950527759 @default.
- W2947030669 cites W2951004968 @default.
- W2947030669 cites W2951101948 @default.
- W2947030669 cites W2952254971 @default.
- W2947030669 cites W2963028280 @default.
- W2947030669 cites W2963095307 @default.
- W2947030669 cites W2963676163 @default.
- W2947030669 cites W2964051675 @default.
- W2947030669 cites W2964108670 @default.
- W2947030669 cites W2964290105 @default.
- W2947030669 cites W2964321699 @default.
- W2947030669 cites W2979481854 @default.
- W2947030669 cites W637153065 @default.
- W2947030669 hasPublicationYear "2019" @default.
- W2947030669 type Work @default.
- W2947030669 sameAs 2947030669 @default.
- W2947030669 citedByCount "9" @default.
- W2947030669 countsByYear W29470306692019 @default.
- W2947030669 countsByYear W29470306692020 @default.
- W2947030669 countsByYear W29470306692021 @default.
- W2947030669 countsByYear W29470306692022 @default.
- W2947030669 crossrefType "posted-content" @default.
- W2947030669 hasAuthorship W2947030669A5012750505 @default.
- W2947030669 hasAuthorship W2947030669A5037753193 @default.
- W2947030669 hasAuthorship W2947030669A5061067204 @default.
- W2947030669 hasAuthorship W2947030669A5064214996 @default.
- W2947030669 hasConcept C101738243 @default.
- W2947030669 hasConcept C119857082 @default.
- W2947030669 hasConcept C132525143 @default.
- W2947030669 hasConcept C13280743 @default.
- W2947030669 hasConcept C154945302 @default.
- W2947030669 hasConcept C17744445 @default.
- W2947030669 hasConcept C185798385 @default.
- W2947030669 hasConcept C199539241 @default.
- W2947030669 hasConcept C205649164 @default.
- W2947030669 hasConcept C2776359362 @default.
- W2947030669 hasConcept C2780022179 @default.
- W2947030669 hasConcept C2781067378 @default.
- W2947030669 hasConcept C41008148 @default.
- W2947030669 hasConcept C50644808 @default.
- W2947030669 hasConcept C70437156 @default.
- W2947030669 hasConcept C80444323 @default.
- W2947030669 hasConcept C94625758 @default.
- W2947030669 hasConceptScore W2947030669C101738243 @default.
- W2947030669 hasConceptScore W2947030669C119857082 @default.
- W2947030669 hasConceptScore W2947030669C132525143 @default.
- W2947030669 hasConceptScore W2947030669C13280743 @default.
- W2947030669 hasConceptScore W2947030669C154945302 @default.
- W2947030669 hasConceptScore W2947030669C17744445 @default.
- W2947030669 hasConceptScore W2947030669C185798385 @default.
- W2947030669 hasConceptScore W2947030669C199539241 @default.
- W2947030669 hasConceptScore W2947030669C205649164 @default.
- W2947030669 hasConceptScore W2947030669C2776359362 @default.
- W2947030669 hasConceptScore W2947030669C2780022179 @default.
- W2947030669 hasConceptScore W2947030669C2781067378 @default.
- W2947030669 hasConceptScore W2947030669C41008148 @default.
- W2947030669 hasConceptScore W2947030669C50644808 @default.
- W2947030669 hasConceptScore W2947030669C70437156 @default.
- W2947030669 hasConceptScore W2947030669C80444323 @default.
- W2947030669 hasConceptScore W2947030669C94625758 @default.
- W2947030669 hasLocation W29470306691 @default.
- W2947030669 hasOpenAccess W2947030669 @default.