mlsanityData to 7 Oct 2026

Robust Hybrid Learning With Expert Augmentation

arXiv 2202.03881 ↗First posted 8 Feb 2022cs.LG stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. Leveraging the insight that the expert model is usually valid even outside the training domain, we overcome this limitation by introducing a hybrid data augmentation strategy termed textitexpert augmentation. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation, which can be incorporated into existing hybrid systems, improves generalization. We empirically validate the expert augmentation on three controlled experiments modelling dynamical systems with ordinary and partial differential equations. Finally, we assess the potential real-world applicability of expert augmentation on a dataset of a real double pendulum.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

28 of 55 references.

References · 28

  1. 2018How Powerful are Graph Neural Networks?cited by 4,355
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  8. 2020In Search of Lost Domain Generalizationcited by 1,042
  9. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  10. 2020Lagrangian Neural Networkscited by 388
  11. 2020Environment Inference for Invariant Learningcited by 306
  12. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
16 more
  1. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  2. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 221
  3. 2020Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Predictioncited by 192
  4. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
  5. 2020Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systemscited by 160
  6. 2021On Calibration and Out-of-domain Generalizationcited by 134
  7. 2020Augmenting Physical Models with Deep Networks for Complex Dynamics Forecastingcited by 93
  8. 2019Sim2real transfer learning for 3D human pose estimation: motion to the rescuecited by 75
  9. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  10. 2021Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progressioncited by 48
  11. 2021A Framework for Machine Learning of Model Error in Dynamical Systemscited by 37
  12. 2021Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networkscited by 20
  13. 2017Sim2Real View Invariant Visual Servoing by Recurrent Controlcited by 19
  14. 2020Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Predictioncited by 18
  15. 2017Aspect-augmented Adversarial Networks for Domain Adaptationcited by 12
  16. 2020Physics-Incorporated Convolutional Recurrent Neural Networks for Source Identification and Forecasting of Dynamical Systemscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 4; 2026: 5.

17 papers.

Sort:

By area:

  1. 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibrationcited by 26
  2. 2025Mixture of Experts (MoE): A Big Data Perspectivecited by 17
  3. 2024Automatically Learning Hybrid Digital Twins of Dynamical Systemscited by 13
  4. 2024The Causal Chambers: Real Physical Systems as a Testbed for AI Methodologycited by 12
  5. 2022Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Modelscited by 6
  6. 2023AI for Science: An Emerging Agendacited by 5
  7. 2025Inductive Domain Transfer In Misspecified Simulation-Based Inferencecited by 4
  8. 2025A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environmentscited by 2
  9. 2026Variational Grey-Box Dynamics Matchingcited by 2
  10. 2023Learning Hybrid Dynamics Models With Simulator-Informed Latent Statescited by 1
  11. 2024PILA: Physics-Informed Low Rank Augmentation for Interpretable Earth Observationcited by 1
  12. 2025Hybrid Generative Modeling for Incomplete Physics: Deep Grey-Box Meets Optimal Transportcited by 1
5 more
  1. 2023Interpretable Mechanistic Representations for Meal-level Glycemic Control in the Wildcited by 0
  2. 2026Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimationcited by 0
  3. 2026HAPI-EP: Towards Hybrid, Adaptive, and Predictive Digital Twins of Cardiac Electrophysiologycited by 0
  4. 2026Learning Cardiac Electrophysiology Digital Twins Through Agentic Discovery of Hybrid Structurecited by 0
  5. 2026Climate Physics Dynamic Matchingcited by 0