Neural Fractional

Neural fractional methods integrate fractional calculus into neural network architectures and algorithms, primarily aiming to improve model performance and robustness by incorporating memory effects and non-local dependencies. Current research focuses on applying these methods to diverse areas, including deep reinforcement learning for optimizing resource allocation (e.g., in mobile edge computing), developing robust graph neural networks, and enhancing the accuracy and efficiency of solving fractional differential equations. This burgeoning field offers the potential for significant advancements in modeling complex systems with memory-dependent behavior, leading to improved accuracy and robustness in various applications such as disease diagnosis and physical system modeling.

Papers

September 25, 2024

Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
Lyudong Jin, Ming Tang, Jiayu Pan, Meng Zhang, Hao Wang
Multi Agent Reinforcement Learning Multi Agent Deep Reinforcement Learning Mobile Edge Computing Single Agent Reinforcement Learning Fractional Derivative Neural Fractional

March 5, 2024

Neural Fractional Differential Equations
C. Coelho, M. Fernanda P. Costa, L. L. Ferrás
Neural ODE Neural Ordinary Differential Equation Neural CDEs Neural Fractional

January 9, 2024

Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
Qiyu Kang, Kai Zhao, Yang Song, Yihang Xie, Yanan Zhao, Sijie Wang, Rui She, Wee Peng Tay
Neural Ordinary Differential Equation Fractional Derivative Robustness Analysis Neural Fractional

December 16, 2023

Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
Lyudong Jin, Ming Tang, Meng Zhang, Hao Wang
Mobile Edge Computing Model Free Deep Reinforcement Learning Neural Fractional

April 26, 2023

Splitting physics-informed neural networks for inferring the dynamics of integer- and fractional-order neuron models
Simin Shekarpaz, Fanhai Zeng, George Karniadakis
Physic Informed Neural Network Neuron Model Split and Fit Integer Arithmetic Neural Fractional

March 13, 2023

Fractional dynamics foster deep learning of COPD stage prediction
Chenzhong Yin, Mihai Udrescu, Gaurav Gupta, Mingxi Cheng, Andrei Lihu, Lucretia Udrescu, Paul Bogdan, David M Mannino, Stefan Mihaicuta
Deep Learning Fractional Derivative Chronic Obstructive Pulmonary Disease Neural Fractional

May 1, 2022

Using a novel fractional-order gradient method for CNN back-propagation
Mundher Mohammed Taresh, Ningbo Zhu, Talal Ahmed Ali Ali, Mohammed Alghaili, Weihua Guo
Back Propagation Fractional Derivative Neural Fractional Fractional Order Gradient

April 18, 2022

An Optimal Time Variable Learning Framework for Deep Neural Networks
Harbir Antil, Hugo Díaz, Evelyn Herberg
Deep Neural Network Data Discretization Feature Propagation Optimal Learning Neural Fractional

February 11, 2022

Algebraic function based Banach space valued ordinary and fractional neural network approximations
George A Anastassiou
Neural Operator Sigmoid Function Banach Space Numerical Approximation Neural Fractional