Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313027578> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4313027578 abstract "While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data. We introduce an Encoded Prior Sliced Wasserstein AutoEncoder wherein an additional prior-encoder network learns a geometry and topology preserving embedding of any data manifold, thus improving the structure of latent space. The autoencoder and prior-encoder networks are iteratively trained using the Sliced Wasserstein distance, which facilitates the learning of nonstandard complex priors. We then introduce a graph-based algorithm to explore the learned manifold by traversing latent space through network-geodesics that lie along the manifold and hence are more realistic compared to conventional Euclidean interpolation. Specifically, we identify network-geodesics by maximizing the density of samples along the path while minimizing total energy. We use the 3D-spiral data to show that the prior encodes the geometry underlying the data unlike conventional autoencoders, and to demonstrate the exploration of the embedded data manifold through the network algorithm. We apply our framework to artificial as well as image datasets to demonstrate the advantages of learning improved latent structure, outlier generation, and geodesic interpolation." @default.
- W4313027578 created "2023-01-06" @default.
- W4313027578 creator A5002601106 @default.
- W4313027578 creator A5081815930 @default.
- W4313027578 date "2022-07-18" @default.
- W4313027578 modified "2023-09-23" @default.
- W4313027578 title "Preserving Data Manifold Structure in Latent Space for Exploration through Network Geodesics" @default.
- W4313027578 cites W1585160083 @default.
- W4313027578 cites W2019106840 @default.
- W4313027578 cites W2169528473 @default.
- W4313027578 cites W2604977777 @default.
- W4313027578 cites W2949649223 @default.
- W4313027578 cites W2963006832 @default.
- W4313027578 cites W2963693826 @default.
- W4313027578 cites W2964231450 @default.
- W4313027578 cites W2979557588 @default.
- W4313027578 cites W3002254693 @default.
- W4313027578 cites W3009854800 @default.
- W4313027578 cites W3034224401 @default.
- W4313027578 cites W3085482458 @default.
- W4313027578 cites W3207971907 @default.
- W4313027578 doi "https://doi.org/10.1109/ijcnn55064.2022.9891993" @default.
- W4313027578 hasPublicationYear "2022" @default.
- W4313027578 type Work @default.
- W4313027578 citedByCount "0" @default.
- W4313027578 crossrefType "proceedings-article" @default.
- W4313027578 hasAuthorship W4313027578A5002601106 @default.
- W4313027578 hasAuthorship W4313027578A5081815930 @default.
- W4313027578 hasConcept C101738243 @default.
- W4313027578 hasConcept C107673813 @default.
- W4313027578 hasConcept C108583219 @default.
- W4313027578 hasConcept C11413529 @default.
- W4313027578 hasConcept C114614502 @default.
- W4313027578 hasConcept C115961682 @default.
- W4313027578 hasConcept C127413603 @default.
- W4313027578 hasConcept C137800194 @default.
- W4313027578 hasConcept C151876577 @default.
- W4313027578 hasConcept C153120616 @default.
- W4313027578 hasConcept C153180895 @default.
- W4313027578 hasConcept C154945302 @default.
- W4313027578 hasConcept C165818556 @default.
- W4313027578 hasConcept C177769412 @default.
- W4313027578 hasConcept C184720557 @default.
- W4313027578 hasConcept C186450821 @default.
- W4313027578 hasConcept C202444582 @default.
- W4313027578 hasConcept C2524010 @default.
- W4313027578 hasConcept C33923547 @default.
- W4313027578 hasConcept C41008148 @default.
- W4313027578 hasConcept C529865628 @default.
- W4313027578 hasConcept C70518039 @default.
- W4313027578 hasConcept C78519656 @default.
- W4313027578 hasConceptScore W4313027578C101738243 @default.
- W4313027578 hasConceptScore W4313027578C107673813 @default.
- W4313027578 hasConceptScore W4313027578C108583219 @default.
- W4313027578 hasConceptScore W4313027578C11413529 @default.
- W4313027578 hasConceptScore W4313027578C114614502 @default.
- W4313027578 hasConceptScore W4313027578C115961682 @default.
- W4313027578 hasConceptScore W4313027578C127413603 @default.
- W4313027578 hasConceptScore W4313027578C137800194 @default.
- W4313027578 hasConceptScore W4313027578C151876577 @default.
- W4313027578 hasConceptScore W4313027578C153120616 @default.
- W4313027578 hasConceptScore W4313027578C153180895 @default.
- W4313027578 hasConceptScore W4313027578C154945302 @default.
- W4313027578 hasConceptScore W4313027578C165818556 @default.
- W4313027578 hasConceptScore W4313027578C177769412 @default.
- W4313027578 hasConceptScore W4313027578C184720557 @default.
- W4313027578 hasConceptScore W4313027578C186450821 @default.
- W4313027578 hasConceptScore W4313027578C202444582 @default.
- W4313027578 hasConceptScore W4313027578C2524010 @default.
- W4313027578 hasConceptScore W4313027578C33923547 @default.
- W4313027578 hasConceptScore W4313027578C41008148 @default.
- W4313027578 hasConceptScore W4313027578C529865628 @default.
- W4313027578 hasConceptScore W4313027578C70518039 @default.
- W4313027578 hasConceptScore W4313027578C78519656 @default.
- W4313027578 hasLocation W43130275781 @default.
- W4313027578 hasOpenAccess W4313027578 @default.
- W4313027578 hasPrimaryLocation W43130275781 @default.
- W4313027578 hasRelatedWork W2115613674 @default.
- W4313027578 hasRelatedWork W2986222199 @default.
- W4313027578 hasRelatedWork W3005973884 @default.
- W4313027578 hasRelatedWork W3027097012 @default.
- W4313027578 hasRelatedWork W3092106794 @default.
- W4313027578 hasRelatedWork W3159953198 @default.
- W4313027578 hasRelatedWork W4287198872 @default.
- W4313027578 hasRelatedWork W4287647544 @default.
- W4313027578 hasRelatedWork W4288027486 @default.
- W4313027578 hasRelatedWork W4313027578 @default.
- W4313027578 isParatext "false" @default.
- W4313027578 isRetracted "false" @default.
- W4313027578 workType "article" @default.