Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening

2022/06/16 by Martín González, Gonzalez, Martin, Hatem Hajri +5
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #I.2.6 #Machine Learning (cs.LG) #Machine Learning in Healthcare #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2206.08237

openalex publication_date 2022/06/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We investigate the problems and challenges of evaluating the robustness of Differential Equation-based (DE) networks against synthetic distribution shifts. We propose a novel and simple accuracy metric which can be used to evaluate intrinsic robustness and to validate dataset corruption simulators. We also propose methodology recommendations, destined for evaluating the many faces of neural DEs' robustness and for comparing them with their discrete counterparts rigorously. We then use this criteria to evaluate a cheap data augmentation technique as a reliable way for demonstrating the natural robustness of neural ODEs against simulated image corruptions across multiple datasets.

Related

• On Robustness of Neural Ordinary Differential Equations
• Efficient Certified Training and Robustness Verification of Neural ODEs
• Ortho-ODE: Enhancing Robustness and of Neural ODEs against Adversarial Attacks
• Stochasticity in Neural ODEs: An Empirical Study
• Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise