Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Characteristic Neural Ordinary Differential Equation
Xingzi Xu, Ali Hasan, Khalil Elkhalil, Jie Ding, Vahid Tarokh
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use C-NODE instead of NODE | Image classification · SVHN | accuracy: $75.28\pm 0.836\%$ -> $\mathbf{82.19\pm 0.478\%}$ | Improved |
| Add C-NODE to ANODE | ANODE · SVHN | accuracy: $89.8\pm0.952\%$ -> $\mathbf{92.23\pm0.176\%}$ | Improved |
| Add C-NODE to IL-NODE | IL-NODE · SVHN | accuracy: $89.69\pm0.369\%$ -> $\mathbf{93.31\pm0.088\%}$ | Improved |
| Use C-NODE instead of NODE | Image classification · CIFAR-10 | accuracy: $56.30\pm 0.742\%$ -> $\mathbf{64.28\pm 0.243\%}$ | Improved |
| Add C-NODE to ANODE | ANODE · CIFAR-10 | accuracy: $70.99\pm 0.483\%$ -> $\mathbf{71.36\pm0.220\%}$ | Improved |
| Add C-NODE to 2nd-Ord | 2nd-Ord · CIFAR-10 | accuracy: $70.84\pm0.360\%$ -> $\mathbf{73.68\pm0.153\%}$ | Improved |
| Add C-NODE to IL-NODE | IL-NODE · CIFAR-10 | accuracy: $72.55\pm0.238\%$ -> $\mathbf{73.78\pm0.154\%}$ | Improved |
| Use C-NODE instead of NODE | Image classification · MNIST | accuracy: $96.90\pm 0.154\%$ -> $\mathbf{97.56\pm 0.431\%}$ | Improved |
| Add C-NODE to ANODE | ANODE · MNIST | accuracy: $99.12\pm 0.021\%$ -> $\mathbf{99.20\pm0.002\%}$ | Improved |
| Add C-NODE to 2nd-Ord | 2nd-Ord · MNIST | accuracy: $99.35\pm0.002\%$ -> $\mathbf{99.38\pm0.037\%}$ | Improved |
| Add C-NODE to IL-NODE | IL-NODE · MNIST | accuracy: $99.33\pm0.039\%$ -> $\mathbf{99.33\pm0.001\%}$ | No clear effect |
| Use C-NODE in place of NODE CNF | Continuous normalizing flow · MNIST, CIFAR-10, and SVHN | Bits/dim: MNIST: $1.00$ -> $\mathbf{0.95}$; CIFAR-10: $3.49$ -> $3.44$; SVHN: $2.15$ -> $\mathbf{2.12}$ | Improved |
Closest papers by meaning
- Symbolic Neural Ordinary Differential Equations (AAAI 2025 · similarity 0.87)
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data (ICLR 2024 · similarity 0.86)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.86)
- KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis (ICML 2025 · similarity 0.86)
- Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024 · similarity 0.86)
- On the Generalization and Approximation Capacities of Neural Controlled Differential Equations (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
