Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119577510> ?p ?o ?g. }
- W3119577510 abstract "We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks. We leverage new insights on defining similarity between graphs as a function of the similarity between their node embedding distributions. Specifically, we use the Wasserstein distance to measure the dissimilarity between node embeddings of different graphs. Unlike prior work, we avoid pairwise calculation of distances between graphs and reduce the computational complexity from quadratic to linear in the number of graphs. WEGL calculates Monge maps from a reference distribution to each node embedding and, based on these maps, creates a fixed-sized vector representation of the graph. We evaluate our new graph embedding approach on various benchmark graph-property prediction tasks, showing state-of-the-art classification performance while having superior computational efficiency." @default.
- W3119577510 created "2021-01-18" @default.
- W3119577510 creator A5041274548 @default.
- W3119577510 creator A5065389164 @default.
- W3119577510 creator A5068682350 @default.
- W3119577510 creator A5090905813 @default.
- W3119577510 date "2021-05-03" @default.
- W3119577510 modified "2023-09-23" @default.
- W3119577510 title "Wasserstein Embedding for Graph Learning" @default.
- W3119577510 cites W1629559917 @default.
- W3119577510 cites W1753775462 @default.
- W3119577510 cites W1816257748 @default.
- W3119577510 cites W1835509607 @default.
- W3119577510 cites W1973289170 @default.
- W3119577510 cites W2094100343 @default.
- W3119577510 cites W2132883347 @default.
- W3119577510 cites W2142498761 @default.
- W3119577510 cites W2147286743 @default.
- W3119577510 cites W2159156271 @default.
- W3119577510 cites W2172478671 @default.
- W3119577510 cites W2303371279 @default.
- W3119577510 cites W2519887557 @default.
- W3119577510 cites W2604795503 @default.
- W3119577510 cites W2735418187 @default.
- W3119577510 cites W2750618092 @default.
- W3119577510 cites W2771949901 @default.
- W3119577510 cites W2788919350 @default.
- W3119577510 cites W2808551187 @default.
- W3119577510 cites W2891771806 @default.
- W3119577510 cites W2909882940 @default.
- W3119577510 cites W2911397097 @default.
- W3119577510 cites W2918342466 @default.
- W3119577510 cites W2945070494 @default.
- W3119577510 cites W2962698288 @default.
- W3119577510 cites W2962711740 @default.
- W3119577510 cites W2962767366 @default.
- W3119577510 cites W2962792820 @default.
- W3119577510 cites W2962810718 @default.
- W3119577510 cites W2962876951 @default.
- W3119577510 cites W2963360524 @default.
- W3119577510 cites W2963477006 @default.
- W3119577510 cites W2963668673 @default.
- W3119577510 cites W2963693932 @default.
- W3119577510 cites W2964145825 @default.
- W3119577510 cites W2964321699 @default.
- W3119577510 cites W2964328909 @default.
- W3119577510 cites W2970406896 @default.
- W3119577510 cites W2970474218 @default.
- W3119577510 cites W2970823238 @default.
- W3119577510 cites W2995983896 @default.
- W3119577510 cites W2996604169 @default.
- W3119577510 cites W3012255272 @default.
- W3119577510 cites W3021954012 @default.
- W3119577510 cites W3022208364 @default.
- W3119577510 cites W3034902920 @default.
- W3119577510 cites W3035649237 @default.
- W3119577510 cites W3036535673 @default.
- W3119577510 cites W3047312226 @default.
- W3119577510 cites W3080088097 @default.
- W3119577510 cites W3083504878 @default.
- W3119577510 cites W3100911650 @default.
- W3119577510 cites W3101183984 @default.
- W3119577510 cites W3103596128 @default.
- W3119577510 cites W3127760629 @default.
- W3119577510 cites W3021975806 @default.
- W3119577510 hasPublicationYear "2021" @default.
- W3119577510 type Work @default.
- W3119577510 sameAs 3119577510 @default.
- W3119577510 citedByCount "4" @default.
- W3119577510 countsByYear W31195775102020 @default.
- W3119577510 countsByYear W31195775102021 @default.
- W3119577510 crossrefType "proceedings-article" @default.
- W3119577510 hasAuthorship W3119577510A5041274548 @default.
- W3119577510 hasAuthorship W3119577510A5065389164 @default.
- W3119577510 hasAuthorship W3119577510A5068682350 @default.
- W3119577510 hasAuthorship W3119577510A5090905813 @default.
- W3119577510 hasConcept C132525143 @default.
- W3119577510 hasConcept C13336665 @default.
- W3119577510 hasConcept C153083717 @default.
- W3119577510 hasConcept C154945302 @default.
- W3119577510 hasConcept C184898388 @default.
- W3119577510 hasConcept C2524010 @default.
- W3119577510 hasConcept C33923547 @default.
- W3119577510 hasConcept C41008148 @default.
- W3119577510 hasConcept C41608201 @default.
- W3119577510 hasConcept C75564084 @default.
- W3119577510 hasConcept C80444323 @default.
- W3119577510 hasConceptScore W3119577510C132525143 @default.
- W3119577510 hasConceptScore W3119577510C13336665 @default.
- W3119577510 hasConceptScore W3119577510C153083717 @default.
- W3119577510 hasConceptScore W3119577510C154945302 @default.
- W3119577510 hasConceptScore W3119577510C184898388 @default.
- W3119577510 hasConceptScore W3119577510C2524010 @default.
- W3119577510 hasConceptScore W3119577510C33923547 @default.
- W3119577510 hasConceptScore W3119577510C41008148 @default.
- W3119577510 hasConceptScore W3119577510C41608201 @default.
- W3119577510 hasConceptScore W3119577510C75564084 @default.
- W3119577510 hasConceptScore W3119577510C80444323 @default.
- W3119577510 hasLocation W31195775101 @default.
- W3119577510 hasOpenAccess W3119577510 @default.