Matches in SemOpenAlex for { <https://semopenalex.org/work/W2995846323> ?p ?o ?g. }
- W2995846323 abstract "Graph convolutional networks (GCNs) have achieved remarkable performance in a variety of network science learning tasks. However, theoretical analysis of such approaches is still at its infancy. Graph scattering transforms (GSTs) are non-trainable deep GCN models that are amenable to generalization and stability analyses. The present work addresses some limitations of GSTs by introducing a novel so-termed pruned (p)GST approach. The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs. It is further established that pGSTs are stable to perturbations of the input graph signals with bounded energy. Experiments showcase that i) pGST performs comparably to the baseline GST that uses all scattering features, while achieving significant computational savings; ii) pGST achieves comparable performance to state-of-the-art GCNs; and iii) Graph data from various domains lead to different scattering patterns, suggesting domain-adaptive pGST network architectures." @default.
- W2995846323 created "2019-12-26" @default.
- W2995846323 creator A5023028617 @default.
- W2995846323 creator A5026758314 @default.
- W2995846323 creator A5066373402 @default.
- W2995846323 date "2020-04-30" @default.
- W2995846323 modified "2023-10-16" @default.
- W2995846323 title "Pruned Graph Scattering Transforms" @default.
- W2995846323 cites W1920022804 @default.
- W2995846323 cites W1994906459 @default.
- W2995846323 cites W2072072671 @default.
- W2995846323 cites W2099486020 @default.
- W2995846323 cites W2099627681 @default.
- W2995846323 cites W2104290444 @default.
- W2995846323 cites W2112090702 @default.
- W2995846323 cites W2117569556 @default.
- W2995846323 cites W2139823104 @default.
- W2995846323 cites W2147286743 @default.
- W2995846323 cites W2158787690 @default.
- W2995846323 cites W2163935396 @default.
- W2995846323 cites W2211722331 @default.
- W2995846323 cites W2558748708 @default.
- W2995846323 cites W2560609797 @default.
- W2995846323 cites W2606202972 @default.
- W2995846323 cites W2788919350 @default.
- W2995846323 cites W2811124557 @default.
- W2995846323 cites W2887344601 @default.
- W2995846323 cites W2933565306 @default.
- W2995846323 cites W2949406091 @default.
- W2995846323 cites W2963121255 @default.
- W2995846323 cites W2963312446 @default.
- W2995846323 cites W2963460103 @default.
- W2995846323 cites W2963693932 @default.
- W2995846323 cites W2963716836 @default.
- W2995846323 cites W2963858333 @default.
- W2995846323 cites W2964015378 @default.
- W2995846323 cites W2964124573 @default.
- W2995846323 cites W2964145825 @default.
- W2995846323 cites W2970695463 @default.
- W2995846323 cites W3104104151 @default.
- W2995846323 hasPublicationYear "2020" @default.
- W2995846323 type Work @default.
- W2995846323 sameAs 2995846323 @default.
- W2995846323 citedByCount "5" @default.
- W2995846323 countsByYear W29958463232020 @default.
- W2995846323 countsByYear W29958463232021 @default.
- W2995846323 crossrefType "proceedings-article" @default.
- W2995846323 hasAuthorship W2995846323A5023028617 @default.
- W2995846323 hasAuthorship W2995846323A5026758314 @default.
- W2995846323 hasAuthorship W2995846323A5066373402 @default.
- W2995846323 hasConcept C108010975 @default.
- W2995846323 hasConcept C11413529 @default.
- W2995846323 hasConcept C120665830 @default.
- W2995846323 hasConcept C121332964 @default.
- W2995846323 hasConcept C132525143 @default.
- W2995846323 hasConcept C134306372 @default.
- W2995846323 hasConcept C154945302 @default.
- W2995846323 hasConcept C191486275 @default.
- W2995846323 hasConcept C33923547 @default.
- W2995846323 hasConcept C34388435 @default.
- W2995846323 hasConcept C41008148 @default.
- W2995846323 hasConcept C6557445 @default.
- W2995846323 hasConcept C80444323 @default.
- W2995846323 hasConcept C86803240 @default.
- W2995846323 hasConceptScore W2995846323C108010975 @default.
- W2995846323 hasConceptScore W2995846323C11413529 @default.
- W2995846323 hasConceptScore W2995846323C120665830 @default.
- W2995846323 hasConceptScore W2995846323C121332964 @default.
- W2995846323 hasConceptScore W2995846323C132525143 @default.
- W2995846323 hasConceptScore W2995846323C134306372 @default.
- W2995846323 hasConceptScore W2995846323C154945302 @default.
- W2995846323 hasConceptScore W2995846323C191486275 @default.
- W2995846323 hasConceptScore W2995846323C33923547 @default.
- W2995846323 hasConceptScore W2995846323C34388435 @default.
- W2995846323 hasConceptScore W2995846323C41008148 @default.
- W2995846323 hasConceptScore W2995846323C6557445 @default.
- W2995846323 hasConceptScore W2995846323C80444323 @default.
- W2995846323 hasConceptScore W2995846323C86803240 @default.
- W2995846323 hasLocation W29958463231 @default.
- W2995846323 hasOpenAccess W2995846323 @default.
- W2995846323 hasPrimaryLocation W29958463231 @default.
- W2995846323 hasRelatedWork W2072072671 @default.
- W2995846323 hasRelatedWork W2101491865 @default.
- W2995846323 hasRelatedWork W2558748708 @default.
- W2995846323 hasRelatedWork W2887344601 @default.
- W2995846323 hasRelatedWork W2949406091 @default.
- W2995846323 hasRelatedWork W2962844340 @default.
- W2995846323 hasRelatedWork W2970695463 @default.
- W2995846323 hasRelatedWork W2973000757 @default.
- W2995846323 hasRelatedWork W3004423099 @default.
- W2995846323 hasRelatedWork W3012644407 @default.
- W2995846323 hasRelatedWork W3012774908 @default.
- W2995846323 hasRelatedWork W3028917156 @default.
- W2995846323 hasRelatedWork W3104104151 @default.
- W2995846323 hasRelatedWork W3104425534 @default.
- W2995846323 hasRelatedWork W3109493217 @default.
- W2995846323 hasRelatedWork W3123559604 @default.
- W2995846323 hasRelatedWork W3124622342 @default.
- W2995846323 hasRelatedWork W3155164980 @default.
- W2995846323 hasRelatedWork W3189078958 @default.