Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203467110> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3203467110 abstract "Network-valued data are encountered in a wide range of applications and pose challenges in learning due to their complex structure and absence of vertex correspondence. Typical examples of such problems include classification or grouping of protein structures and social networks. Various methods, ranging from graph kernels to graph neural networks, have been proposed that achieve some success in graph classification problems. However, most methods have limited theoretical justification, and their applicability beyond classification remains unexplored. In this work, we propose methods for clustering multiple graphs, without vertex correspondence, that are inspired by the recent literature on estimating graphons -- symmetric functions corresponding to infinite vertex limit of graphs. We propose a novel graph distance based on sorting-and-smoothing graphon estimators. Using the proposed graph distance, we present two clustering algorithms and show that they achieve state-of-the-art results. We prove the statistical consistency of both algorithms under Lipschitz assumptions on the graph degrees. We further study the applicability of the proposed distance for graph two-sample testing problems." @default.
- W3203467110 created "2021-10-11" @default.
- W3203467110 creator A5052425916 @default.
- W3203467110 creator A5064168352 @default.
- W3203467110 creator A5076078733 @default.
- W3203467110 date "2021-10-06" @default.
- W3203467110 modified "2023-09-27" @default.
- W3203467110 title "Graphon based Clustering and Testing of Networks: Algorithms and Theory." @default.
- W3203467110 cites W1519192496 @default.
- W3203467110 cites W1983681808 @default.
- W3203467110 cites W1996881001 @default.
- W3203467110 cites W2008857988 @default.
- W3203467110 cites W2012459404 @default.
- W3203467110 cites W2064274783 @default.
- W3203467110 cites W2082734581 @default.
- W3203467110 cites W2092750499 @default.
- W3203467110 cites W2099438806 @default.
- W3203467110 cites W2118323338 @default.
- W3203467110 cites W2132914434 @default.
- W3203467110 cites W2142498761 @default.
- W3203467110 cites W2148606196 @default.
- W3203467110 cites W2166524953 @default.
- W3203467110 cites W2170607286 @default.
- W3203467110 cites W2222512263 @default.
- W3203467110 cites W2303371279 @default.
- W3203467110 cites W2343790552 @default.
- W3203467110 cites W2404258945 @default.
- W3203467110 cites W2595583675 @default.
- W3203467110 cites W2614531606 @default.
- W3203467110 cites W2737925311 @default.
- W3203467110 cites W2889790583 @default.
- W3203467110 cites W2952264420 @default.
- W3203467110 cites W2962711740 @default.
- W3203467110 cites W2962719258 @default.
- W3203467110 cites W2962962954 @default.
- W3203467110 cites W2963806077 @default.
- W3203467110 cites W2964316034 @default.
- W3203467110 cites W2970474218 @default.
- W3203467110 cites W2970823238 @default.
- W3203467110 cites W3032776603 @default.
- W3203467110 cites W3093943311 @default.
- W3203467110 cites W3105663802 @default.
- W3203467110 cites W3110694252 @default.
- W3203467110 cites W3141303149 @default.
- W3203467110 cites W2136040699 @default.
- W3203467110 hasPublicationYear "2021" @default.
- W3203467110 type Work @default.
- W3203467110 sameAs 3203467110 @default.
- W3203467110 citedByCount "0" @default.
- W3203467110 crossrefType "posted-content" @default.
- W3203467110 hasAuthorship W3203467110A5052425916 @default.
- W3203467110 hasAuthorship W3203467110A5064168352 @default.
- W3203467110 hasAuthorship W3203467110A5076078733 @default.
- W3203467110 hasConcept C11413529 @default.
- W3203467110 hasConcept C132525143 @default.
- W3203467110 hasConcept C154945302 @default.
- W3203467110 hasConcept C22047676 @default.
- W3203467110 hasConcept C31972630 @default.
- W3203467110 hasConcept C3770464 @default.
- W3203467110 hasConcept C41008148 @default.
- W3203467110 hasConcept C73555534 @default.
- W3203467110 hasConcept C80444323 @default.
- W3203467110 hasConcept C80899671 @default.
- W3203467110 hasConceptScore W3203467110C11413529 @default.
- W3203467110 hasConceptScore W3203467110C132525143 @default.
- W3203467110 hasConceptScore W3203467110C154945302 @default.
- W3203467110 hasConceptScore W3203467110C22047676 @default.
- W3203467110 hasConceptScore W3203467110C31972630 @default.
- W3203467110 hasConceptScore W3203467110C3770464 @default.
- W3203467110 hasConceptScore W3203467110C41008148 @default.
- W3203467110 hasConceptScore W3203467110C73555534 @default.
- W3203467110 hasConceptScore W3203467110C80444323 @default.
- W3203467110 hasConceptScore W3203467110C80899671 @default.
- W3203467110 hasLocation W32034671101 @default.
- W3203467110 hasOpenAccess W3203467110 @default.
- W3203467110 hasPrimaryLocation W32034671101 @default.
- W3203467110 hasRelatedWork W1541648315 @default.
- W3203467110 hasRelatedWork W1642186374 @default.
- W3203467110 hasRelatedWork W2116477200 @default.
- W3203467110 hasRelatedWork W2133909049 @default.
- W3203467110 hasRelatedWork W2474535028 @default.
- W3203467110 hasRelatedWork W2565761069 @default.
- W3203467110 hasRelatedWork W2803654897 @default.
- W3203467110 hasRelatedWork W2804381853 @default.
- W3203467110 hasRelatedWork W2931671159 @default.
- W3203467110 hasRelatedWork W2948839854 @default.
- W3203467110 hasRelatedWork W2951824725 @default.
- W3203467110 hasRelatedWork W2954348559 @default.
- W3203467110 hasRelatedWork W2963749288 @default.
- W3203467110 hasRelatedWork W2966087175 @default.
- W3203467110 hasRelatedWork W2980948168 @default.
- W3203467110 hasRelatedWork W2985434080 @default.
- W3203467110 hasRelatedWork W3008760144 @default.
- W3203467110 hasRelatedWork W3088507067 @default.
- W3203467110 hasRelatedWork W3094102025 @default.
- W3203467110 hasRelatedWork W3159273858 @default.
- W3203467110 isParatext "false" @default.
- W3203467110 isRetracted "false" @default.
- W3203467110 magId "3203467110" @default.
- W3203467110 workType "article" @default.