FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2995315221> ?p ?o ?g. }

• W2995315221 abstract "It has been shown that using geometric spaces with non-zero curvature instead of plain Euclidean spaces with zero curvature improves performance on a range of Machine Learning tasks for learning representations. Recent work has leveraged these geometries to learn latent variable models like Variational Autoencoders (VAEs) in spherical and hyperbolic spaces with constant curvature. While these approaches work well on particular kinds of data that they were designed for e.g.~tree-like data for a hyperbolic VAE, there exists no generic approach unifying all three models. We develop a Mixed-curvature Variational Autoencoder, an efficient way to train a VAE whose latent space is a product of constant curvature Riemannian manifolds, where the per-component curvature can be learned. This generalizes the Euclidean VAE to curved latent spaces, as the model essentially reduces to the Euclidean VAE if curvatures of all latent space components go to 0." @default.
• W2995315221 created "2019-12-26" @default.
• W2995315221 creator A5026343324 @default.
• W2995315221 creator A5037156810 @default.
• W2995315221 creator A5064290471 @default.
• W2995315221 date "2020-04-30" @default.
• W2995315221 modified "2023-09-27" @default.
• W2995315221 title "Mixed-curvature Variational Autoencoders" @default.
• W2995315221 cites W1594816962 @default.
• W2995315221 cites W1909320841 @default.
• W2995315221 cites W1949248870 @default.
• W2995315221 cites W1959608418 @default.
• W2995315221 cites W1969002377 @default.
• W2995315221 cites W2001070843 @default.
• W2995315221 cites W2032558547 @default.
• W2995315221 cites W2096192494 @default.
• W2995315221 cites W2099471712 @default.
• W2995315221 cites W2105776550 @default.
• W2995315221 cites W2128728535 @default.
• W2995315221 cites W2194321275 @default.
• W2995315221 cites W2467604901 @default.
• W2995315221 cites W2519536754 @default.
• W2995315221 cites W2555641442 @default.
• W2995315221 cites W2558748708 @default.
• W2995315221 cites W2560512785 @default.
• W2995315221 cites W2588715987 @default.
• W2995315221 cites W2753738274 @default.
• W2995315221 cites W2803760543 @default.
• W2995315221 cites W2808409763 @default.
• W2995315221 cites W2891234799 @default.
• W2995315221 cites W2903538854 @default.
• W2995315221 cites W2919594328 @default.
• W2995315221 cites W2923452197 @default.
• W2995315221 cites W2933374552 @default.
• W2995315221 cites W2949502795 @default.
• W2995315221 cites W2962911072 @default.
• W2995315221 cites W2962918699 @default.
• W2995315221 cites W2962936818 @default.
• W2995315221 cites W2963081964 @default.
• W2995315221 cites W2963090522 @default.
• W2995315221 cites W2963223306 @default.
• W2995315221 cites W2963275229 @default.
• W2995315221 cites W2963841265 @default.
• W2995315221 cites W2963849380 @default.
• W2995315221 cites W2964011399 @default.
• W2995315221 cites W2964050265 @default.
• W2995315221 cites W2964108670 @default.
• W2995315221 cites W2964109691 @default.
• W2995315221 cites W2964121744 @default.
• W2995315221 cites W2964311827 @default.
• W2995315221 cites W2964343746 @default.
• W2995315221 cites W2984925782 @default.
• W2995315221 cites W3102317997 @default.
• W2995315221 cites W3118608800 @default.
• W2995315221 cites W81361445 @default.
• W2995315221 cites W2963448675 @default.
• W2995315221 doi "https://doi.org/10.3929/ethz-b-000372387" @default.
• W2995315221 hasPublicationYear "2020" @default.
• W2995315221 type Work @default.
• W2995315221 sameAs 2995315221 @default.
• W2995315221 citedByCount "4" @default.
• W2995315221 countsByYear W29953152212020 @default.
• W2995315221 countsByYear W29953152212021 @default.
• W2995315221 crossrefType "proceedings-article" @default.
• W2995315221 hasAuthorship W2995315221A5026343324 @default.
• W2995315221 hasAuthorship W2995315221A5037156810 @default.
• W2995315221 hasAuthorship W2995315221A5064290471 @default.
• W2995315221 hasConcept C101738243 @default.
• W2995315221 hasConcept C111919701 @default.
• W2995315221 hasConcept C129782007 @default.
• W2995315221 hasConcept C154945302 @default.
• W2995315221 hasConcept C175017881 @default.
• W2995315221 hasConcept C186450821 @default.
• W2995315221 hasConcept C195065555 @default.
• W2995315221 hasConcept C199360897 @default.
• W2995315221 hasConcept C202444582 @default.
• W2995315221 hasConcept C2524010 @default.
• W2995315221 hasConcept C2777027219 @default.
• W2995315221 hasConcept C2778572836 @default.
• W2995315221 hasConcept C2779668893 @default.
• W2995315221 hasConcept C33923547 @default.
• W2995315221 hasConcept C41008148 @default.
• W2995315221 hasConcept C50644808 @default.
• W2995315221 hasConcept C83677898 @default.
• W2995315221 hasConceptScore W2995315221C101738243 @default.
• W2995315221 hasConceptScore W2995315221C111919701 @default.
• W2995315221 hasConceptScore W2995315221C129782007 @default.
• W2995315221 hasConceptScore W2995315221C154945302 @default.
• W2995315221 hasConceptScore W2995315221C175017881 @default.
• W2995315221 hasConceptScore W2995315221C186450821 @default.
• W2995315221 hasConceptScore W2995315221C195065555 @default.
• W2995315221 hasConceptScore W2995315221C199360897 @default.
• W2995315221 hasConceptScore W2995315221C202444582 @default.
• W2995315221 hasConceptScore W2995315221C2524010 @default.
• W2995315221 hasConceptScore W2995315221C2777027219 @default.
• W2995315221 hasConceptScore W2995315221C2778572836 @default.
• W2995315221 hasConceptScore W2995315221C2779668893 @default.
• W2995315221 hasConceptScore W2995315221C33923547 @default.
• W2995315221 hasConceptScore W2995315221C41008148 @default.
• W2995315221 hasConceptScore W2995315221C50644808 @default.

• next