Encoded Prior Sliced Wasserstein AutoEncoder for learning latent\n manifold representations Article Swipe

MAKE IMPACT

Sanjukta Krishnagopal , Jacob Bedrossian · YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2010.01037

While variational autoencoders have been successful in several tasks, the use\nof conventional priors are limited in their ability to encode the underlying\nstructure of input data. We introduce an Encoded Prior Sliced Wasserstein\nAutoEncoder wherein an additional prior-encoder network learns an embedding of\nthe data manifold which preserves topological and geometric properties of the\ndata, thus improving the structure of latent space. The autoencoder and\nprior-encoder networks are iteratively trained using the Sliced Wasserstein\ndistance. The effectiveness of the learned manifold encoding is explored by\ntraversing latent space through interpolations along geodesics which generate\nsamples that lie on the data manifold and hence are more realistic compared to\nEuclidean interpolation. To this end, we introduce a graph-based algorithm for\nexploring the data manifold and interpolating along network-geodesics in latent\nspace by maximizing the density of samples along the path while minimizing\ntotal energy. We use the 3D-spiral data to show that the prior encodes the\ngeometry underlying the data unlike conventional autoencoders, and to\ndemonstrate the exploration of the embedded data manifold through the network\nalgorithm. We apply our framework to benchmarked image datasets to demonstrate\nthe advantages of learning data representations in outlier generation, latent\nstructure, and geodesic interpolation.\n

Type

preprint

Landing Page

http://arxiv.org/abs/2010.01037

PDF

https://arxiv.org/pdf/2010.01037

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4287647544

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4287647544

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2010.01037

Digital Object Identifier

Title

Encoded Prior Sliced Wasserstein AutoEncoder for learning latent\n manifold representations

Work title

Type

preprint

OpenAlex work type

Publication year

2020

Year of publication

Publication date

2020-10-02

Full publication date if available

Authors

Sanjukta Krishnagopal, Jacob Bedrossian

List of authors in order

Landing page

https://arxiv.org/abs/2010.01037

Publisher landing page

PDF URL

https://arxiv.org/pdf/2010.01037

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2010.01037

Direct OA link when available

Concepts

Autoencoder, Geodesic, Manifold alignment, Manifold (fluid mechanics), Nonlinear dimensionality reduction, Interpolation (computer graphics), Artificial intelligence, Euclidean space, Computer science, Mathematics, Prior probability, Algorithm, Pattern recognition (psychology), Topology (electrical circuits), Deep learning, Dimensionality reduction, Image (mathematics), Geometry, Combinatorics, Mechanical engineering, Engineering, Bayesian probability

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload