arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.15210cs.LGmath.AT
收藏

一种用于拓扑机器学习的Transformer结构

Persformer: A Transformer Architecture for Topological Machine Learning

Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);L2F SA(L2F公司)

Raphael Reinauer, Matteo Caorsi, Nicolas Berkouk

摘要:

拓扑数据分析(TDA)的主要挑战之一是从持久图中提取机器学习算法直接可用的特征。实际上,持久性图本质上是$\mathbb{R}^2$中的点的(多)集合,并且不能以直接的方式被视为向量。在本文中,我们将介绍$\texttt{Persformer}$,它是第一个接受持久性图作为输入的Transformer神经网络体系结构。$\texttt{Persformer}$架构在经典合成和图形基准数据集上的性能显著优于以前的拓扑神经网络架构。此外,它还满足一个普适逼近定理。这使我们能够介绍拓扑机器学习的第一个可解释性方法,我们在两个例子中探索。

英文摘要:

One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in $\mathbb{R}^2$ and cannot be seen in a straightforward manner as vectors. In this article, we introduce $\texttt{Persformer}$, the first Transformer neural network architecture that accepts persistence diagrams as input. The $\texttt{Persformer}$ architecture significantly outperforms previous topological neural network architectures on classical synthetic and graph benchmark datasets. Moreover, it satisfies a universal approximation theorem. This allows us to introduce the first interpretability method for topological machine learning, which we explore in two examples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑