GINN-KAN: Interpretability pipelining with applications in Physics Informed Neural Networks
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RDVAIMETrecord.jsonopen to challenge →
read the original abstract
Neural networks are powerful function approximators, yet their ``black-box" nature often renders them opaque and difficult to interpret. While many post-hoc explanation methods exist, they typically fail to capture the underlying reasoning processes of the networks. A truly interpretable neural network would be trained similarly to conventional models using techniques such as backpropagation, but additionally provide insights into the learned input-output relationships. In this work, we introduce the concept of interpretability pipelineing, to incorporate multiple interpretability techniques to outperform each individual technique. To this end, we first evaluate several architectures that promise such interpretability, with a particular focus on two recent models selected for their potential to incorporate interpretability into standard neural network architectures while still leveraging backpropagation: the Growing Interpretable Neural Network (GINN) and Kolmogorov Arnold Networks (KAN). We analyze the limitations and strengths of each and introduce a novel interpretable neural network GINN-KAN that synthesizes the advantages of both models. When tested on the Feynman symbolic regression benchmark datasets, GINN-KAN outperforms both GINN and KAN. To highlight the capabilities and the generalizability of this approach, we position GINN-KAN as an alternative to conventional black-box networks in Physics-Informed Neural Networks (PINNs). We expect this to have far-reaching implications in the application of deep learning pipelines in the natural sciences. Our experiments with this interpretable PINN on 15 different partial differential equations demonstrate that GINN-KAN augmented PINNs outperform PINNs with black-box networks in solving differential equations and surpass the capabilities of both GINN and KAN.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks
For two-layer KANs trained with gradient descent under logistic loss and NTK-separable assumption, polylogarithmic width suffices for 1/T optimization and 1/n generalization rates, while differential privacy requires ...
-
Bayesian Analysis Using a Constrained Mixture of Normal-Inverse-Gamma Models
A constrained mixture of Normal-Inverse-Gamma models allows direct sampling of parameters given labels and uses preliminary estimators to restrict label space for feasible Bayesian inference without full MCMC.
-
Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
Element-Weighted KANs achieve state-of-the-art accuracy on formation energy, band gap, and work function while revealing periodic-table-aligned chemical trends through their learnable activation functions.
-
A Practitioner's Guide to Kolmogorov-Arnold Networks
A systematic review of Kolmogorov-Arnold Networks that maps their relation to Kolmogorov superposition theory, MLPs, and kernels, examines basis-function design choices, summarizes performance advances, and supplies a...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.