Prospects of federated machine learning in fluid dynamics

  title={Prospects of federated machine learning in fluid dynamics},
  author={Omer San and Suraj Pawar and Adil Rasheed},
Physics-based models have been mainstream in fluid dynamics for developing predictive models. In recent years, machine learning has offered a renaissance to the fluid community due to the rapid developments in data science, processing units, neural network based technologies, and sensor adaptations. So far in many applications in fluid dynamics, machine learning approaches have been mostly focused on a standard process that requires centralizing the training data on a designated machine or in a… 

Figures from this paper



Model fusion with physics-guided machine learning: Projection-based reduced-order modeling

A physics-guided machine learning (PGML) framework that leverages the interpretable physics-based model with a deep learning model and is capable of enhancing the generalizability of data-driven models and effectively protects against or inform about the inaccurate predictions resulting from extrapolation is put forth.

Data-driven recovery of hidden physics in reduced order modeling of fluid flows

A modular hybrid analysis and modeling approach to account for hidden physics in reduced order modeling of parameterized systems relevant to fluid dynamics provides insights addressing a fundamental limitation of the physics-based models when the governing equations are incomplete to represent underlying physical processes.

Federated Optimization in Heterogeneous Networks

This work introduces a framework, FedProx, to tackle heterogeneity in federated networks, and provides convergence guarantees for this framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work.

Nonlinear proper orthogonal decomposition for convection-dominated flows

A nonlinear proper orthogonal decomposition (POD) framework, which is an end-to-end Galerkin-free model combining autoencoders with long short-term memory networks for dynamics, which not only improves the accuracy, but also significantly reduces the computational cost of training and testing.

Towards Personalized Federated Learning

This survey explores the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets.

Deep learning to discover and predict dynamics on an inertial manifold

A data-driven framework is developed to represent chaotic dynamics on an inertial manifold and applied to solutions of the Kuramoto-Sivashinsky equation, reproducing very well key dynamic and statistical features of the attractor.

Personalized Federated Learning: A Meta-Learning Approach

A personalized variant of the well-known Federated Averaging algorithm is studied and its performance is characterized by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.

Adaptive Personalized Federated Learning

Information theoretically, it is proved that the mixture of local and global models can reduce the generalization error and a communication-reduced bilevel optimization method is proposed, which reduces the communication rounds to $O(\sqrt{T})$ and can achieve a convergence rate of $O(1/T)$ with some residual error.

Fair Resource Allocation in Federated Learning

This work proposes q-Fair Federated Learning (q-FFL), a novel optimization objective inspired by fair resource allocation in wireless networks that encourages a more fair accuracy distribution across devices in federated networks.