Saved in:
Bibliographic Details
Main Authors: Carvallo, Ciro, Bocaccio, Hernán, Mindlin, Gabriel B., Groisman, Pablo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916830556192768
author Carvallo, Ciro
Bocaccio, Hernán
Mindlin, Gabriel B.
Groisman, Pablo
author_facet Carvallo, Ciro
Bocaccio, Hernán
Mindlin, Gabriel B.
Groisman, Pablo
contents We present a method for reconstructing evolutionary trees from high-dimensional data, with a specific application to bird song spectrograms. We address the challenge of inferring phylogenetic relationships from phenotypic traits, like vocalizations, without predefined acoustic properties. Our approach combines two main components: Poincaré embeddings for dimensionality reduction and distance computation, and the neighbor joining algorithm for tree reconstruction. Unlike previous work, we employ Siamese networks to learn embeddings from only leaf node samples of the latent tree. We demonstrate our method's effectiveness on both synthetic data and spectrograms from six species of finches.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Siamese networks for Poincaré embeddings and the reconstruction of evolutionary trees
Carvallo, Ciro
Bocaccio, Hernán
Mindlin, Gabriel B.
Groisman, Pablo
Populations and Evolution
Machine Learning
We present a method for reconstructing evolutionary trees from high-dimensional data, with a specific application to bird song spectrograms. We address the challenge of inferring phylogenetic relationships from phenotypic traits, like vocalizations, without predefined acoustic properties. Our approach combines two main components: Poincaré embeddings for dimensionality reduction and distance computation, and the neighbor joining algorithm for tree reconstruction. Unlike previous work, we employ Siamese networks to learn embeddings from only leaf node samples of the latent tree. We demonstrate our method's effectiveness on both synthetic data and spectrograms from six species of finches.
title Siamese networks for Poincaré embeddings and the reconstruction of evolutionary trees
topic Populations and Evolution
Machine Learning
url https://arxiv.org/abs/2410.07387