Minimum spanning trees are widely used graph structures used to find relationships between data organized in a graph. This work proposes a new approach based on neural networks, in particular, autoencoders, to extrapolate this tree from the dissimilarity representation of the data, seen as a noisy version of the minimum spanning tree. After many tests done on different network, the final results confirm the validity of the idea.

Minimum spanning tree reconstruction using autoencoders

Castelletto, Riccardo
2020/2021

Abstract

Minimum spanning trees are widely used graph structures used to find relationships between data organized in a graph. This work proposes a new approach based on neural networks, in particular, autoencoders, to extrapolate this tree from the dissimilarity representation of the data, seen as a noisy version of the minimum spanning tree. After many tests done on different network, the final results confirm the validity of the idea.
2020-01-07
autoencoder, spanning
File in questo prodotto:
File Dimensione Formato  
Minimum_spanning_tree_reconstruction_using_autoencoders.pdf

accesso aperto

Dimensione 5.18 MB
Formato Adobe PDF
5.18 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/22905