Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912189568> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2912189568 abstract "A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines, describing chemical compounds, surfaces of three-dimensional models, social interactions, or knowledge bases, to name only a few. There is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on arbitrary graph-structured data directly. The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts that work well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions.First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure.Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details.Third, we present GraphVAE, a graph generator allowing us to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation." @default.
- W2912189568 created "2019-02-21" @default.
- W2912189568 creator A5026733401 @default.
- W2912189568 date "2018-12-14" @default.
- W2912189568 modified "2023-09-24" @default.
- W2912189568 title "Deep Learning on Attributed Graphs" @default.
- W2912189568 hasPublicationYear "2018" @default.
- W2912189568 type Work @default.
- W2912189568 sameAs 2912189568 @default.
- W2912189568 citedByCount "0" @default.
- W2912189568 crossrefType "dissertation" @default.
- W2912189568 hasAuthorship W2912189568A5026733401 @default.
- W2912189568 hasConcept C11413529 @default.
- W2912189568 hasConcept C131979681 @default.
- W2912189568 hasConcept C132525143 @default.
- W2912189568 hasConcept C154945302 @default.
- W2912189568 hasConcept C187691185 @default.
- W2912189568 hasConcept C203776342 @default.
- W2912189568 hasConcept C2524010 @default.
- W2912189568 hasConcept C33923547 @default.
- W2912189568 hasConcept C41008148 @default.
- W2912189568 hasConcept C41608201 @default.
- W2912189568 hasConcept C43517604 @default.
- W2912189568 hasConcept C68103157 @default.
- W2912189568 hasConcept C80444323 @default.
- W2912189568 hasConceptScore W2912189568C11413529 @default.
- W2912189568 hasConceptScore W2912189568C131979681 @default.
- W2912189568 hasConceptScore W2912189568C132525143 @default.
- W2912189568 hasConceptScore W2912189568C154945302 @default.
- W2912189568 hasConceptScore W2912189568C187691185 @default.
- W2912189568 hasConceptScore W2912189568C203776342 @default.
- W2912189568 hasConceptScore W2912189568C2524010 @default.
- W2912189568 hasConceptScore W2912189568C33923547 @default.
- W2912189568 hasConceptScore W2912189568C41008148 @default.
- W2912189568 hasConceptScore W2912189568C41608201 @default.
- W2912189568 hasConceptScore W2912189568C43517604 @default.
- W2912189568 hasConceptScore W2912189568C68103157 @default.
- W2912189568 hasConceptScore W2912189568C80444323 @default.
- W2912189568 hasLocation W29121895681 @default.
- W2912189568 hasOpenAccess W2912189568 @default.
- W2912189568 hasPrimaryLocation W29121895681 @default.
- W2912189568 hasRelatedWork W1795355757 @default.
- W2912189568 hasRelatedWork W2264126668 @default.
- W2912189568 hasRelatedWork W2398592859 @default.
- W2912189568 hasRelatedWork W24570487 @default.
- W2912189568 hasRelatedWork W2759093587 @default.
- W2912189568 hasRelatedWork W2779302908 @default.
- W2912189568 hasRelatedWork W2805019413 @default.
- W2912189568 hasRelatedWork W2904630684 @default.
- W2912189568 hasRelatedWork W2911591567 @default.
- W2912189568 hasRelatedWork W2944833253 @default.
- W2912189568 hasRelatedWork W2946851410 @default.
- W2912189568 hasRelatedWork W2963555845 @default.
- W2912189568 hasRelatedWork W2969617491 @default.
- W2912189568 hasRelatedWork W2997710324 @default.
- W2912189568 hasRelatedWork W3034409935 @default.
- W2912189568 hasRelatedWork W3081079206 @default.
- W2912189568 hasRelatedWork W3094552683 @default.
- W2912189568 hasRelatedWork W3118398624 @default.
- W2912189568 hasRelatedWork W598319177 @default.
- W2912189568 hasRelatedWork W842665618 @default.
- W2912189568 isParatext "false" @default.
- W2912189568 isRetracted "false" @default.
- W2912189568 magId "2912189568" @default.
- W2912189568 workType "dissertation" @default.