mlsanityData to 14 Oct 2026

Automatic and Structure-Aware Sparsification of Hybrid Neural ODEs

arXiv 2505.18996 ↗First posted 25 May 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Hybrid neural ordinary differential equations (neural ODEs) integrate mechanistic models with neural ODEs, offering strong inductive bias and flexibility, and are particularly advantageous in data-scarce healthcare settings. However, excessive latent states and interactions from mechanistic models can lead to training inefficiency and over-fitting, limiting practical effectiveness of hybrid neural ODEs. In response, we propose a new hybrid pipeline for automatic state selection and structure optimization in mechanistic neural ODEs, combining domain-informed graph modifications with data-driven regularization to sparsify the model for improving predictive performance and stability while retaining mechanistic plausibility. Experiments on synthetic and real-world data show improved predictive performance and robustness with desired sparsity, establishing an effective solution for hybrid model reduction in healthcare applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 70 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

25 of 70 references.

References · 25

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  3. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  4. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
  5. 2019The State of Sparsity in Deep Neural Networkscited by 476
  6. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
  7. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  8. 2017Stable Architectures for Deep Neural Networkscited by 341
  9. 2022On Neural Differential Equationscited by 268
  10. 2018Techniques for Interpretable Machine Learningcited by 238
  11. 2016Temporal Convolutional Networks: A Unified Approach to Action Segmentationcited by 199
  12. 2019Graph Neural Ordinary Differential Equationscited by 154
13 more
  1. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 98
  2. 2019LassoNet: A Neural Network with Feature Sparsitycited by 82
  3. 2021Stiff Neural Ordinary Differential Equationscited by 78
  4. 2020Graph Structure of Neural Networkscited by 68
  5. 2019The Generalization-Stability Tradeoff In Neural Network Pruningcited by 54
  6. 2021Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progressioncited by 48
  7. 2023A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learningcited by 24
  8. 2020Neural Closure Models for Dynamical Systemscited by 22
  9. 2020Neural Ordinary Differential Equations for Intervention Modelingcited by 19
  10. 2020Learning Insulin-Glucose Dynamics in the Wildcited by 15
  11. 2021Neural Pharmacodynamic State Space Modelingcited by 12
  12. 2019Learning Robust Representations with Graph Denoising Policy Networkcited by 10
  13. 2023The Contextual Lasso: Sparse Linear Models via Deep Neural Networkscited by 6

Built on by

Not cited yet.