Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890571755> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2890571755 abstract "Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. pairwise distances tend to not reflect semantic similarities well. This renders unsupervised tasks, such as clustering, difficult when working with the latent representations. We demonstrate that taking the geometry of the generative model into account is sufficient to make simple clustering algorithms work well over latent representations. Leaning on the recent finding that deep generative models constitute stochastically immersed Riemannian manifolds, we propose an efficient algorithm for computing geodesics (shortest paths) and computing distances in the latent space, while taking its distortion into account. We further propose a new architecture for modeling uncertainty in variational autoencoders, which is essential for understanding the geometry of deep generative models. Experiments show that the geodesic distance is very likely to reflect the internal structure of the data." @default.
- W2890571755 created "2018-09-27" @default.
- W2890571755 creator A5012875707 @default.
- W2890571755 creator A5016681542 @default.
- W2890571755 creator A5023214008 @default.
- W2890571755 creator A5033546888 @default.
- W2890571755 creator A5072186051 @default.
- W2890571755 date "2018-09-13" @default.
- W2890571755 modified "2023-10-18" @default.
- W2890571755 title "Geodesic Clustering in Deep Generative Models." @default.
- W2890571755 cites W1909320841 @default.
- W2890571755 cites W1959608418 @default.
- W2890571755 cites W2132914434 @default.
- W2890571755 cites W2533545350 @default.
- W2890571755 cites W2949416428 @default.
- W2890571755 cites W2951523806 @default.
- W2890571755 cites W2964011399 @default.
- W2890571755 hasPublicationYear "2018" @default.
- W2890571755 type Work @default.
- W2890571755 sameAs 2890571755 @default.
- W2890571755 citedByCount "10" @default.
- W2890571755 countsByYear W28905717552018 @default.
- W2890571755 countsByYear W28905717552019 @default.
- W2890571755 countsByYear W28905717552020 @default.
- W2890571755 countsByYear W28905717552021 @default.
- W2890571755 crossrefType "posted-content" @default.
- W2890571755 hasAuthorship W2890571755A5012875707 @default.
- W2890571755 hasAuthorship W2890571755A5016681542 @default.
- W2890571755 hasAuthorship W2890571755A5023214008 @default.
- W2890571755 hasAuthorship W2890571755A5033546888 @default.
- W2890571755 hasAuthorship W2890571755A5072186051 @default.
- W2890571755 hasConcept C108583219 @default.
- W2890571755 hasConcept C111472728 @default.
- W2890571755 hasConcept C11413529 @default.
- W2890571755 hasConcept C138885662 @default.
- W2890571755 hasConcept C153180895 @default.
- W2890571755 hasConcept C154945302 @default.
- W2890571755 hasConcept C165818556 @default.
- W2890571755 hasConcept C167966045 @default.
- W2890571755 hasConcept C184898388 @default.
- W2890571755 hasConcept C2524010 @default.
- W2890571755 hasConcept C2780586882 @default.
- W2890571755 hasConcept C33923547 @default.
- W2890571755 hasConcept C39890363 @default.
- W2890571755 hasConcept C41008148 @default.
- W2890571755 hasConcept C73555534 @default.
- W2890571755 hasConcept C80444323 @default.
- W2890571755 hasConceptScore W2890571755C108583219 @default.
- W2890571755 hasConceptScore W2890571755C111472728 @default.
- W2890571755 hasConceptScore W2890571755C11413529 @default.
- W2890571755 hasConceptScore W2890571755C138885662 @default.
- W2890571755 hasConceptScore W2890571755C153180895 @default.
- W2890571755 hasConceptScore W2890571755C154945302 @default.
- W2890571755 hasConceptScore W2890571755C165818556 @default.
- W2890571755 hasConceptScore W2890571755C167966045 @default.
- W2890571755 hasConceptScore W2890571755C184898388 @default.
- W2890571755 hasConceptScore W2890571755C2524010 @default.
- W2890571755 hasConceptScore W2890571755C2780586882 @default.
- W2890571755 hasConceptScore W2890571755C33923547 @default.
- W2890571755 hasConceptScore W2890571755C39890363 @default.
- W2890571755 hasConceptScore W2890571755C41008148 @default.
- W2890571755 hasConceptScore W2890571755C73555534 @default.
- W2890571755 hasConceptScore W2890571755C80444323 @default.
- W2890571755 hasLocation W28905717551 @default.
- W2890571755 hasOpenAccess W2890571755 @default.
- W2890571755 hasPrimaryLocation W28905717551 @default.
- W2890571755 hasRelatedWork W147969812 @default.
- W2890571755 hasRelatedWork W1959608418 @default.
- W2890571755 hasRelatedWork W2099471712 @default.
- W2890571755 hasRelatedWork W2766856052 @default.
- W2890571755 hasRelatedWork W2798914089 @default.
- W2890571755 hasRelatedWork W2914711327 @default.
- W2890571755 hasRelatedWork W2962897886 @default.
- W2890571755 hasRelatedWork W2963289229 @default.
- W2890571755 hasRelatedWork W2964011399 @default.
- W2890571755 hasRelatedWork W2964231450 @default.
- W2890571755 hasRelatedWork W2965344674 @default.
- W2890571755 hasRelatedWork W2979915069 @default.
- W2890571755 hasRelatedWork W2988402696 @default.
- W2890571755 hasRelatedWork W2994486311 @default.
- W2890571755 hasRelatedWork W2994851293 @default.
- W2890571755 hasRelatedWork W3007345776 @default.
- W2890571755 hasRelatedWork W3021414772 @default.
- W2890571755 hasRelatedWork W3160317769 @default.
- W2890571755 hasRelatedWork W3171859092 @default.
- W2890571755 hasRelatedWork W3178198544 @default.
- W2890571755 isParatext "false" @default.
- W2890571755 isRetracted "false" @default.
- W2890571755 magId "2890571755" @default.
- W2890571755 workType "article" @default.