Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035079703> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3035079703 endingPage "2312" @default.
- W3035079703 startingPage "2302" @default.
- W3035079703 abstract "Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However current deep neural methods suffer from limited scalability: for a graph with $n$ nodes and $m$ edges, existing deep neural methods require $Omega(n^2)$ complexity by building up the adjacency matrix. On the other hand, many real world graphs are actually sparse in the sense that $mll n^2$. Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency matrix, and importantly reduces the graph generation time complexity to $O((n + m)log n)$. Furthermore, during training this autoregressive model can be parallelized with $O(log n)$ synchronization stages, which makes it much more efficient than other autoregressive models that require $Omega(n)$. Experiments on several benchmarks show that the proposed approach not only scales to orders of magnitude larger graphs than previously possible with deep autoregressive graph generative models, but also yields better graph generation quality." @default.
- W3035079703 created "2020-06-19" @default.
- W3035079703 creator A5010575626 @default.
- W3035079703 creator A5039679910 @default.
- W3035079703 creator A5040269658 @default.
- W3035079703 creator A5070035154 @default.
- W3035079703 creator A5086484914 @default.
- W3035079703 date "2020-07-12" @default.
- W3035079703 modified "2023-09-27" @default.
- W3035079703 title "Scalable Deep Generative Modeling for Sparse Graphs" @default.
- W3035079703 hasPublicationYear "2020" @default.
- W3035079703 type Work @default.
- W3035079703 sameAs 3035079703 @default.
- W3035079703 citedByCount "5" @default.
- W3035079703 countsByYear W30350797032020 @default.
- W3035079703 countsByYear W30350797032021 @default.
- W3035079703 crossrefType "proceedings-article" @default.
- W3035079703 hasAuthorship W3035079703A5010575626 @default.
- W3035079703 hasAuthorship W3035079703A5039679910 @default.
- W3035079703 hasAuthorship W3035079703A5040269658 @default.
- W3035079703 hasAuthorship W3035079703A5070035154 @default.
- W3035079703 hasAuthorship W3035079703A5086484914 @default.
- W3035079703 hasConcept C108583219 @default.
- W3035079703 hasConcept C11413529 @default.
- W3035079703 hasConcept C119857082 @default.
- W3035079703 hasConcept C132525143 @default.
- W3035079703 hasConcept C149782125 @default.
- W3035079703 hasConcept C154945302 @default.
- W3035079703 hasConcept C159877910 @default.
- W3035079703 hasConcept C167966045 @default.
- W3035079703 hasConcept C180356752 @default.
- W3035079703 hasConcept C33923547 @default.
- W3035079703 hasConcept C39890363 @default.
- W3035079703 hasConcept C41008148 @default.
- W3035079703 hasConcept C48044578 @default.
- W3035079703 hasConcept C77088390 @default.
- W3035079703 hasConcept C80444323 @default.
- W3035079703 hasConceptScore W3035079703C108583219 @default.
- W3035079703 hasConceptScore W3035079703C11413529 @default.
- W3035079703 hasConceptScore W3035079703C119857082 @default.
- W3035079703 hasConceptScore W3035079703C132525143 @default.
- W3035079703 hasConceptScore W3035079703C149782125 @default.
- W3035079703 hasConceptScore W3035079703C154945302 @default.
- W3035079703 hasConceptScore W3035079703C159877910 @default.
- W3035079703 hasConceptScore W3035079703C167966045 @default.
- W3035079703 hasConceptScore W3035079703C180356752 @default.
- W3035079703 hasConceptScore W3035079703C33923547 @default.
- W3035079703 hasConceptScore W3035079703C39890363 @default.
- W3035079703 hasConceptScore W3035079703C41008148 @default.
- W3035079703 hasConceptScore W3035079703C48044578 @default.
- W3035079703 hasConceptScore W3035079703C77088390 @default.
- W3035079703 hasConceptScore W3035079703C80444323 @default.
- W3035079703 hasLocation W30350797031 @default.
- W3035079703 hasOpenAccess W3035079703 @default.
- W3035079703 hasPrimaryLocation W30350797031 @default.
- W3035079703 hasRelatedWork W2076723445 @default.
- W3035079703 hasRelatedWork W2397751796 @default.
- W3035079703 hasRelatedWork W2436151787 @default.
- W3035079703 hasRelatedWork W2554952599 @default.
- W3035079703 hasRelatedWork W2565761069 @default.
- W3035079703 hasRelatedWork W2614038188 @default.
- W3035079703 hasRelatedWork W2742123199 @default.
- W3035079703 hasRelatedWork W2786103815 @default.
- W3035079703 hasRelatedWork W2804381853 @default.
- W3035079703 hasRelatedWork W2807319024 @default.
- W3035079703 hasRelatedWork W2944916185 @default.
- W3035079703 hasRelatedWork W2949988865 @default.
- W3035079703 hasRelatedWork W2970709315 @default.
- W3035079703 hasRelatedWork W2994860160 @default.
- W3035079703 hasRelatedWork W3008760144 @default.
- W3035079703 hasRelatedWork W3037783566 @default.
- W3035079703 hasRelatedWork W3103250330 @default.
- W3035079703 hasRelatedWork W3118010192 @default.
- W3035079703 hasRelatedWork W3172199627 @default.
- W3035079703 hasRelatedWork W3177248227 @default.
- W3035079703 hasVolume "1" @default.
- W3035079703 isParatext "false" @default.
- W3035079703 isRetracted "false" @default.
- W3035079703 magId "3035079703" @default.
- W3035079703 workType "article" @default.