{rfName}
De

Indexed in

License and use

Citations

Altmetrics

Analysis of institutional authors

Fernandez Pascual, AngelaAuthorDorronsoro JAuthor

Share

October 25, 2019
Publications
>
Proceedings Paper
No

Deep Diffusion Autoencoders

Publicated to:Proceedings of the International Joint Conference on Neural Networks. 2019-July - 2019-07-01 2019-July(), DOI: 10.1109/IJCNN.2019.8852168

Authors: Dorado S; Fernandez A; Dorronsoro J

Affiliations

2 ;‎ Univ Autonoma Madrid, Inst Ingn Conocimiento, Madrid 28049, Spain - Author
1 ;‎ Univ Autonoma Madrid, Dept Comp Engn, Madrid 28049, Spain - Author
Universidad Autónoma de Madrid - Author

Abstract

© 2019 IEEE. Extending work by Mishne et al. [1], we propose Deep Diffusion Autoencoders (DDA) that learn an encoder-decoder map using a composite loss function that simultaneously minimizes the reconstruction error at the output layer and the distance to a Diffusion Map embedding in the bottleneck layer. These DDA are thus able to reconstruct new patterns from points in the embedding space in a way that preserves the geometry of the sample and, as a consequence, our experiments show that they may provide a powerful tool for data augmentation.

Keywords

Neural-networks

Quality index

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2025-07-24:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 7 (PlumX).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (Dorado S) and Last Author (DORRONSORO IBERO, JOSE RAMON).