Robust Convolution Neural ODEs via Contractivity-promoting regularization

• URL: http://arxiv.org/abs/2508.11432v1
• Date: Fri, 15 Aug 2025 12:18:44 GMT
• Title: Robust Convolution Neural ODEs via Contractivity-promoting regularization
• Authors: Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate,
• Abstract summary: We propose to use contraction theory to improve robustness of neural networks represented by dynamical systems.<n>Contractivity can be induced during training by using a regularization term involving the Jacobian of the system dynamics.<n>We show that it can also be promoted using carefully selected weight regularization terms for a class of NODEs with slope-restricted activation functions.
• Score: 8.60855254087051
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks can be fragile to input noise and adversarial attacks. In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems, and propose to use contraction theory to improve their robustness. For a contractive dynamical system two trajectories starting from different initial conditions converge to each other exponentially fast. Contractive Convolutional NODEs can enjoy increased robustness as slight perturbations of the features do not cause a significant change in the output. Contractivity can be induced during training by using a regularization term involving the Jacobian of the system dynamics. To reduce the computational burden, we show that it can also be promoted using carefully selected weight regularization terms for a class of NODEs with slope-restricted activation functions. The performance of the proposed regularizers is illustrated through benchmark image classification tasks on MNIST and FashionMNIST datasets, where images are corrupted by different kinds of noise and attacks.

Related papers

• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Neuronal Group Communication for Efficient Neural representation [85.36421257648294]
  This paper addresses the question of how to build large neural systems that learn efficient, modular, and interpretable representations.<n>We propose Neuronal Group Communication (NGC), a theory-driven framework that reimagines a neural network as a dynamical system of interacting neuronal groups.<n>NGC treats weights as transient interactions between embedding-like neuronal states, with neural computation unfolding through iterative communication among groups of neurons.
  arXiv  Detail & Related papers  (2025-10-19T14:23:35Z)
• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Low-Rank Implicit Neural Representation via Schatten-p Quasi-Norm and Jacobian Regularization [49.158601255093416]
  We propose a CP-based low-rank tensor function parameterized by neural networks for implicit neural representation.<n>For smoothness, we propose a regularization term based on the spectral norm of the Jacobian and Hutchinson's trace estimator.<n>Our proposed smoothness regularization is SVD-free and avoids explicit chain rule derivations.
  arXiv  Detail & Related papers  (2025-06-27T11:23:10Z)
• Certified Neural Approximations of Nonlinear Dynamics [52.79163248326912]
  In safety-critical contexts, the use of neural approximations requires formal bounds on their closeness to the underlying system.<n>We propose a novel, adaptive, and parallelizable verification method based on certified first-order models.
  arXiv  Detail & Related papers  (2025-05-21T13:22:20Z)
• A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks [18.185834696177654]
  Oversmoothing in Graph Neural Networks (GNNs) poses a significant challenge as network depth increases.<n>We identify the root causes of oversmoothing and propose textbftextitDYNAMO-GAT.<n>Our theoretical analysis reveals how DYNAMO-GAT disrupts the convergence to oversmoothed states.
  arXiv  Detail & Related papers  (2024-12-10T07:07:06Z)
• Neural Delay Differential Equations: System Reconstruction and Image Classification [14.59919398960571]
  We propose a new class of continuous-depth neural networks with delay, named Neural Delay Differential Equations (NDDEs) Compared to NODEs, NDDEs have a stronger capacity of nonlinear representations. We achieve lower loss and higher accuracy not only for the data produced synthetically but also for the CIFAR10, a well-known image dataset.
  arXiv  Detail & Related papers  (2023-04-11T16:09:28Z)
• Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations [0.9437165725355698]
  We introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. We show how to endow our proposed NodeRENs with contractivity and dissipativity -- crucial properties for robust learning and control.
  arXiv  Detail & Related papers  (2023-04-06T10:02:54Z)
• On Robust Classification using Contractive Hamiltonian Neural ODEs [8.049462923912902]
  We employ contraction theory to improve robustness of neural ODEs (NODEs) In NODEs, the input data corresponds to the initial condition of dynamical systems. We propose a class of contractive Hamiltonian NODEs (CH-NODEs)
  arXiv  Detail & Related papers  (2022-03-22T15:16:36Z)
• Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics [73.77459272878025]
  We propose to enhance the supervised signal in learning dynamics by pre-training a neural differential operator (NDO) NDO is pre-trained on a class of symbolic functions, and it learns the mapping between the trajectory samples of these functions to their derivatives. We provide theoretical guarantee on that the output of NDO can well approximate the ground truth derivatives by proper tuning the complexity of the library.
  arXiv  Detail & Related papers  (2021-06-08T08:04:47Z)
• Operational vs Convolutional Neural Networks for Image Denoising [25.838282412957675]
  Convolutional Neural Networks (CNNs) have recently become a favored technique for image denoising due to its adaptive learning ability. We propose a heterogeneous network model which allows greater flexibility for embedding additional non-linearity at the core of the data transformation. An extensive set of comparative evaluations of ONNs and CNNs over two severe image denoising problems yield conclusive evidence that ONNs enriched by non-linear operators can achieve a superior denoising performance against CNNs with both equivalent and well-known deep configurations.
  arXiv  Detail & Related papers  (2020-09-01T12:15:28Z)
• Time Dependence in Non-Autonomous Neural ODEs [74.78386661760662]
  We propose a novel family of Neural ODEs with time-varying weights. We outperform previous Neural ODE variants in both speed and representational capacity.
  arXiv  Detail & Related papers  (2020-05-05T01:41:46Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.