Neural Partial Differential Equations with Functional Convolution
Not on the map. Why?
Abstract (arXiv)
We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs. Our key idea is to leverage the prior of ``translational similarity'' of numerical PDE differential operators to drastically reduce the scale of learning model and training data. We implemented three central network components, including a neural functional convolution operator, a Picard forward iterative procedure, and an adjoint backward gradient calculator. Our novel paradigm fully leverages the multifaceted priors that stem from the sparse and smooth nature of the physical PDE solution manifold and the various mature numerical techniques such as adjoint solver, linearization, and iterative procedure to accelerate the computation. We demonstrate the efficacy of our method by robustly discovering the model and accurately predicting the solutions of various types of PDEs with small-scale networks and training sets. We highlight that all the PDE examples we showed were trained with up to 8 data samples and within 325 network parameters.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 10 Mar 2023.
Builds on
27 of 40 references.
References · 27
- 2018Neural Ordinary Differential Equationscited by 3,733
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2019DeepXDE: A deep learning library for solving differential equationscited by 617
- 2013Network In Networkcited by 600
- 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
- 2017Solving high-dimensional partial differential equations using deep learningcited by 549
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
- 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
- 2019Machine Learning for Fluid Mechanicscited by 380
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2017PDE-Net: Learning PDEs from Datacited by 304
15 more
- 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 208
- 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
- 2018Flexible Neural Representation for Physics Predictioncited by 91
- 2019Learning Neural PDE Solvers with Convergence Guaranteescited by 77
- 2019Learning Compositional Koopman Operators for Model-Based Controlcited by 67
- 2018Propagation Networks for Model-Based Control Under Partial Observationcited by 64
- 2018Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equationscited by 54
- 2016Deep Learning Approximation for Stochastic Control Problemscited by 51
- 2018Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncingcited by 36
- 2019Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systemscited by 33
- 2020Solving inverse-PDE problems with physics-aware neural networkscited by 27
- 2018Neural-net-induced Gaussian process regression for function approximation and PDE solutioncited by 22
- 2019Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learningcited by 15
- 2020FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equationscited by 14
- 2019Coercing Machine Learning to Output Physically Accurate Resultscited by 10
Built on by
Citing papers per year: 2024: 1.
1 paper.