Nonparametric Topological Layers in Neural Networks

TL;DR

This paper introduces a learnable topological layer for neural networks that operates on general metric spaces, eliminating the need for Euclidean parametrization and hyperparameters, thus simplifying implementation and potentially improving performance.

Contribution

It proposes a novel topological layer that functions on metric spaces without Euclidean assumptions, removing hyperparameters and reducing parametrization complexity.

Findings

Eliminates the need for Euclidean space in topological layers

Reduces hyperparameter tuning and parametrization time

Enables more flexible and potentially more effective neural network architectures

Abstract

Various topological techniques and tools have been applied to neural networks in terms of network complexity, explainability, and performance. One fundamental assumption of this line of research is the existence of a global (Euclidean) coordinate system upon which the topological layer is constructed. Despite promising results, such a \textit{topologization} method has yet to be widely adopted because the parametrization of a topologization layer takes a considerable amount of time and more importantly, lacks a theoretical foundation without which the performance of the neural network only achieves suboptimal performance. This paper proposes a learnable topological layer for neural networks without requiring a Euclidean space; Instead, the proposed construction requires nothing more than a general metric space except for an inner product, i.e., a Hilbert space. Accordingly, the according parametrization for the proposed topological layer is free of user-specified hyperparameters, which precludes the costly parametrization stage and the corresponding possibility of suboptimal networks.