A Topological Regularizer for Classifiers via Persistent Homology

Abstract

Regularization plays a crucial role in supervised learning. Most existing methods enforce a global regularization in a structure agnostic manner. In this paper, we initiate a new direction and propose to enforce the structural simplicity of the classification boundary by regularizing over its topological complexity. In particular, our measurement of topological complexity incorporates the importance of topological features (e.g., connected components, handles, and so on) in a meaningful manner, and provides a direct control over spurious topological structures. We incorporate the new measurement as a topological penalty in training classifiers. We also pro- pose an efficient algorithm to compute the gradient of such penalty. Our method pro- vides a novel way to topologically simplify the global structure of the model, without having to sacrifice too much of the flexibility of the model. We demonstrate the effectiveness of our new topological regularizer on a range of synthetic and real-world datasets.

Cited by in corpus (23)

• Topology-Preserving Deep Image Segmentation
• A Topology Layer for Machine Learning
• A Topological Machine Learning Pipeline for Classification
• Topological Learning for Brain Networks
• Wasserstein Stability for Persistence Diagrams
• Optimizing persistent homology based functions
• Path homologies of deep feedforward networks
• Topology-Aware Segmentation Using Discrete Morse Theory
• Localization in the Crowd with Topological Constraints
• Trigger Hunting with a Topological Prior for Trojan Detection
• Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks
• Reviews: Topological Distances and Losses for Brain Networks
• Topological Detection of Trojaned Neural Networks
• Regularization of Persistent Homology Gradient Computation
• Topologically penalized regression on manifolds
• Topological Node2vec: Enhanced Graph Embedding via Persistent Homology
• Robust Persistence Diagrams using Reproducing Kernels
• Some Geometrical and Topological Properties of DNNs' Decision Boundaries
• Graph Filtration Learning
• Accelerating Iterated Persistent Homology Computations with Warm Starts
• Nonparametric Topological Layers in Neural Networks
• Topological Regularization for Dense Prediction
• Topologically Densified Distributions