Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320458190> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4320458190 abstract "Graph convolutional networks (GCNs) can successfully learn the graph signal representation by graph convolution. The graph convolution depends on the graph filter, which contains the topological dependency of data and propagates data features. However, the estimation errors in the propagation matrix (e.g., the adjacency matrix) can have a significant impact on graph filters and GCNs. In this paper, we study the effect of a probabilistic graph error model on the performance of the GCNs. We prove that the adjacency matrix under the error model is bounded by a function of graph size and error probability. We further analytically specify the upper bound of a normalized adjacency matrix with self-loop added. Finally, we illustrate the error bounds by running experiments on a synthetic dataset and study the sensitivity of a simple GCN under this probabilistic error model on accuracy." @default.
- W4320458190 created "2023-02-14" @default.
- W4320458190 creator A5027129265 @default.
- W4320458190 creator A5031785324 @default.
- W4320458190 creator A5055234860 @default.
- W4320458190 date "2022-03-15" @default.
- W4320458190 modified "2023-09-26" @default.
- W4320458190 title "Graph Neural Network Sensitivity Under Probabilistic Error Model" @default.
- W4320458190 doi "https://doi.org/10.48550/arxiv.2203.07831" @default.
- W4320458190 hasPublicationYear "2022" @default.
- W4320458190 type Work @default.
- W4320458190 citedByCount "0" @default.
- W4320458190 crossrefType "posted-content" @default.
- W4320458190 hasAuthorship W4320458190A5027129265 @default.
- W4320458190 hasAuthorship W4320458190A5031785324 @default.
- W4320458190 hasAuthorship W4320458190A5055234860 @default.
- W4320458190 hasBestOaLocation W43204581901 @default.
- W4320458190 hasConcept C110484373 @default.
- W4320458190 hasConcept C11413529 @default.
- W4320458190 hasConcept C132525143 @default.
- W4320458190 hasConcept C154945302 @default.
- W4320458190 hasConcept C180356752 @default.
- W4320458190 hasConcept C203776342 @default.
- W4320458190 hasConcept C22149727 @default.
- W4320458190 hasConcept C33923547 @default.
- W4320458190 hasConcept C41008148 @default.
- W4320458190 hasConcept C49937458 @default.
- W4320458190 hasConcept C78913703 @default.
- W4320458190 hasConcept C80444323 @default.
- W4320458190 hasConceptScore W4320458190C110484373 @default.
- W4320458190 hasConceptScore W4320458190C11413529 @default.
- W4320458190 hasConceptScore W4320458190C132525143 @default.
- W4320458190 hasConceptScore W4320458190C154945302 @default.
- W4320458190 hasConceptScore W4320458190C180356752 @default.
- W4320458190 hasConceptScore W4320458190C203776342 @default.
- W4320458190 hasConceptScore W4320458190C22149727 @default.
- W4320458190 hasConceptScore W4320458190C33923547 @default.
- W4320458190 hasConceptScore W4320458190C41008148 @default.
- W4320458190 hasConceptScore W4320458190C49937458 @default.
- W4320458190 hasConceptScore W4320458190C78913703 @default.
- W4320458190 hasConceptScore W4320458190C80444323 @default.
- W4320458190 hasLocation W43204581901 @default.
- W4320458190 hasLocation W43204581902 @default.
- W4320458190 hasLocation W43204581903 @default.
- W4320458190 hasOpenAccess W4320458190 @default.
- W4320458190 hasPrimaryLocation W43204581901 @default.
- W4320458190 hasRelatedWork W2276438615 @default.
- W4320458190 hasRelatedWork W2351723517 @default.
- W4320458190 hasRelatedWork W2372027113 @default.
- W4320458190 hasRelatedWork W2383534452 @default.
- W4320458190 hasRelatedWork W2606072185 @default.
- W4320458190 hasRelatedWork W2765955582 @default.
- W4320458190 hasRelatedWork W3177365930 @default.
- W4320458190 hasRelatedWork W4318995835 @default.
- W4320458190 hasRelatedWork W4321854624 @default.
- W4320458190 hasRelatedWork W4380877261 @default.
- W4320458190 isParatext "false" @default.
- W4320458190 isRetracted "false" @default.
- W4320458190 workType "article" @default.