MMODELYST
Papers/Phylogenetic Tree Inference with Tropical Axial Attention
PAP

Phylogenetic Tree Inference with Tropical Axial Attention

May 12, 2026

arXiv
Abstract

In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus operators, inducing a piecewise-linear structure aligned with dynamic programming formulations. From multi-species sequence alignments, our model learns all possible pairwise distances and is trained using a combination of $\ell_1$ and tropical symmetric distance metric losses with an ultrametric violation penalty. We leverage the well known isomorphic relationship between the space of all phylogenetic trees with $n$ species and tropical Grassmannian to show that tropical attention provides a natural geometric framework for phylogenetic inference. On empirical $DS1-DS11$ alignments, where true trees are unknown, the tropical model produces distance matrices that are substantially closer to their BME-induced tree metrics than the baseline models. These results suggest that tropical attention is a useful geometric inductive bias for neural phylogenetic inference, especially under distribution shift and when tree-metric consistency is important.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Chris Teska, Kurt Pasque, Ruriko Yoshida, Baran Hashemi
Your notes (browser-local)
saved
arXiv:2605.13894