Derivation of Back-propagation for Graph Convolutional Networks using Matrix Calculus and its Application to Explainable Artificial Intelligence
Authors:
Preprint
Abstract
This paper provides a comprehensive and detailed derivation of the backpropagation algorithm for graph convolutional neural networks using matrix calculus. The derivation is extended to include arbitrary element-wise activation functions and an arbitrary number of layers. The study addresses two fundamental problems, namely node classification and link prediction. To validate our method, we compare it with reverse-mode automatic differentiation. The experimental results demonstrate that the median sum of squared errors of the updated weight matrices, when comparing our method to the approach using reverse-mode automatic differentiation, falls within the range of $10^{-18}$ to $10^{-14}$. These outcomes are obtained from conducting experiments on a five-layer graph convolutional network, applied to a node classification problem on Zachary's karate club social network and a link prediction problem on a drug-drug interaction network. Finally, we show how the derived closed-form solution can facilitate the development of explainable AI and sensitivity analysis.
Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Random permutation-based mixed-double scrambling technique for encrypting MQIR imageJournal of Applied Physics, 2024
- Interpreting Black-Box Models: A Review on Explainable Artificial IntelligenceCognitive Computation, 2023
- A Comparison of Global Sensitivity Analysis Methods for Explainable AI With an Application in Genomic PredictionIEEE Access, 2022
- A survey on graph-based deep learning for computational histopathologyComputerized Medical Imaging and Graphics, 2022
- KEGG mapping tools for uncovering hidden features in biological dataProtein Science, 2021
- Imbalanced Host Response to SARS-CoV-2 Drives Development of COVID-19Cell, 2020
- Matplotlib: A 2D Graphics EnvironmentComputing in Science & Engineering, 2007
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988
- Kronecker products and matrix calculus in system theoryIEEE Transactions on Circuits and Systems, 1978