Automated Manifold Learning for Reduced Order Modeling

2025/06/02 by Imran Nasim, Melanie Weber, Nasim, Imran +1
Engineering · Physics and Astronomy · #FOS: Computer and information sciences #Hydraulic and Pneumatic Systems #Machine Learning (cs.LG) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2506.01741

openalex publication_date 2025/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The problem of identifying geometric structure in data is a cornerstone of (unsupervised) learning. As a result, Geometric Representation Learning has been widely applied across scientific and engineering domains. In this work, we investigate the use of Geometric Representation Learning for the data-driven discovery of system dynamics from spatial-temporal data. We propose to encode similarity structure in such data in a spatial-temporal proximity graph, to which we apply a range of classical and deep learning-based manifold learning approaches to learn reduced order dynamics. We observe that while manifold learning is generally capable of recovering reduced order dynamics, the quality of the learned representations varies substantially across different algorithms and hyperparameter choices. This is indicative of high sensitivity to the inherent geometric assumptions of the respective approaches and suggests a need for careful hyperparameter tuning, which can be expensive in practise. To overcome these challenges, we propose a framework for Automated Manifold Learning, which selects a manifold learning approach and corresponding hyperparameter choices based on representative subsamples of the input graph. We demonstrate that the proposed framework leads to performance gains both in scalability and in the learned representations' accuracy in capturing local and global geometric features of the underlying system dynamics.

Citations

• Using Neural Implicit Flow To Represent Latent Dynamics Of Canonical Systems
• TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets
• Discovering Governing Equations from Partial Measurements with Deep Delay Autoencoders
• Identifying the latent space geometry of network models through analysis of curvature
• Efficient AutoML Pipeline Search with Matrix and Tensor Factorization
• Neighborhood Growth Determines Geometric Priors for Relational Representation Learning
• Dynamic Graph CNN for Learning on Point Clouds
• Dynamic Graph CNN for Learning on Point Clouds
• Linearly-Recurrent Autoencoder Networks for Learning Dynamics
• Graph Attention Networks
• An introduction to Topological Data Analysis: fundamental and practical\n aspects for data scientists
• Inductive Representation Learning on Large Graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• node2vec: Scalable Feature Learning for Networks
• DeepWalk: Online Learning of Social Representations
• Practical Bayesian Optimization of Machine Learning Algorithms
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Exact Solution of the Sine-Gordon Equation for Multiple Collisions of Solitons
• Multidimensional Scaling by Optimizing Goodness of Fit to a Nonmetric Hypothesis

Related

• Learning physics-based reduced-order models from data using nonlinear manifolds
• A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics
• Connecting Neural Models Latent Geometries with Relative Geodesic Representations
• Geometric Principles for Machine Learning of Dynamical Systems
• Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systems