用热带注意力建模进化树，显著提升距离预测精度。
Phylogenetic Tree Inference with Tropical Axial Attention
- 用max-plus运算替代传统注意力，契合动态规划结构。
- 在DS1-DS11数据集上，平均误差比Phyloformer低81.5%。
- 适合需要树度量一致性的进化推断任务。
本文提出一种热带轴向注意力神经推理架构，以max-plus运算替代标准softmax点积注意力，形成与动态规划形式对齐的分段线性结构。基于多物种序列比对，模型学习所有可能的成对距离，并结合ℓ₁损失、热带对称距离损失及超度量违反惩罚进行训练。利用n个物种的进化树空间与热带格拉斯曼流形之间的同构关系，证明热带注意力为进化推断提供了自然的几何框架。在真实树未知的DS1-DS11比对数据上，该模型在每项数据集上的平均绝对误差（MAE）均低于FastME诱导的树度量，相较于Phyloformer降低81.5%，相比Phyloformer 2降低98.4%。结果表明，热带注意力是神经进化推断中有效的几何归纳偏置，尤其适用于分布外场景及树度量一致性要求高的情况。
原文摘要 · Abstract (English)
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 achieves the lowest MAE to its FastME-induced tree metric on every dataset, with a MAE reductions averaging 81.5% relative to Phyloformer and 98.4% relative than Phyloformer 2. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。