GENEOnet: Statistical analysis supporting explainability and trustworthiness

2025-03-12

AI Summary

This work addresses the challenge of lacking statistically rigorous validation for model interpretability, trustworthiness, and robustness in explainable artificial intelligence (XAI) for computational biochemistry. We propose and empirically validate GENEOnet—a novel interpretable neural network built upon Group Equivariant Non-Expansive Operators (GENEOs). To systematically verify the theoretical advantages of GENEO-based architectures, we introduce the first integrated evaluation framework combining parameter sensitivity analysis, quantitative equivariance assessment, and molecular dynamics–based perturbation experiments. Results demonstrate that GENEOnet exhibits highly interpretable parameters, achieves significantly higher equivariance ratios than baseline methods, and maintains exceptional robustness under structural perturbations—evidenced by average performance degradation of less than 5%. This study provides the first cross-dimensional, reproducible, and statistically validated empirical evidence supporting the application of GENEOs in trustworthy AI for computational biochemistry.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Group Equivariant Non-Expansive Operators (GENEOs) have emerged as mathematical tools for constructing networks for Machine Learning and Artificial Intelligence. Recent findings suggest that such models can be inserted within the domain of eXplainable Artificial Intelligence (XAI) due to their inherent interpretability. In this study, we aim to verify this claim with respect to GENEOnet, a GENEO network developed for an application in computational biochemistry by employing various statistical analyses and experiments. Such experiments first allow us to perform a sensitivity analysis on GENEOnet's parameters to test their significance. Subsequently, we show that GENEOnet exhibits a significantly higher proportion of equivariance compared to other methods. Lastly, we demonstrate that GENEOnet is on average robust to perturbations arising from molecular dynamics. These results collectively serve as proof of the explainability, trustworthiness, and robustness of GENEOnet and confirm the beneficial use of GENEOs in the context of Trustworthy Artificial Intelligence.

Problem

• Assessing GENEOnet's explainability in computational biochemistry.
• Evaluating GENEOnet's robustness to molecular dynamics perturbations.
• Comparing GENEOnet's equivariance with other methods.

Innovation

• GENEOs enhance explainability in AI networks.
• GENEOnet shows high equivariance in statistical tests.
• GENEOnet robust against molecular dynamics perturbations.