PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

TL;DR

PhyloVAE introduces an unsupervised deep learning framework that effectively learns high-resolution representations and generates phylogenetic trees rapidly, overcoming limitations of traditional distance-based methods.

Contribution

It presents a novel variational autoencoder model tailored for phylogenetic trees, enabling efficient, high-resolution representation learning and fast topology generation.

Findings

Demonstrates robust representation learning of phylogenetic trees.

Enables fast, parallelized topology generation.

Outperforms classical methods in resolution and speed.

Abstract

Learning informative representations of phylogenetic tree structures is essential for analyzing evolutionary relationships. Classical distance-based methods have been widely used to project phylogenetic trees into Euclidean space, but they are often sensitive to the choice of distance metric and may lack sufficient resolution. In this paper, we introduce phylogenetic variational autoencoders (PhyloVAEs), an unsupervised learning framework designed for representation learning and generative modeling of tree topologies. Leveraging an efficient encoding mechanism inspired by autoregressive tree topology generation, we develop a deep latent-variable generative model that facilitates fast, parallelized topology generation. PhyloVAE combines this generative model with a collaborative inference model based on learnable topological features, allowing for high-resolution representations of phylogenetic tree samples. Extensive experiments demonstrate PhyloVAE's robust representation learning capabilities and fast generation of phylogenetic tree topologies.