GENEOnet: Statistical analysis supporting explainability and trustworthiness

• URL: http://arxiv.org/abs/2503.09199v1
• Date: Wed, 12 Mar 2025 09:43:48 GMT
• Title: GENEOnet: Statistical analysis supporting explainability and trustworthiness
• Authors: Giovanni Bocchi, Patrizio Frosini, Alessandra Micheletti, Alessandro Pedretti, Carmen Gratteri, Filippo Lunghini, Andrea Rosario Beccari, Carmine Talarico,
• Abstract summary: Group Equivariant Non-Expansive Operators (GENEOs) have emerged as mathematical tools for constructing networks for Machine Learning and Artificial Intelligence.<n>Recent findings suggest that such models can be inserted within the domain of eXplainable Artificial Intelligence (XAI) due to their inherent interpretability.
• Score: 67.410870290301
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles [0.0]
  Machine-learned potentials (MLPs) have revolutionized materials discovery by providing accurate and efficient predictions of molecular and material properties. Graph Neural Networks (GNNs) have emerged as a state-of-the-art approach due to their ability to capture complex atomic interactions. This work highlights the potential of lightweight Uncertainty Quantification (UQ) methods in improving the robustness of GNN-based materials modeling.
  arXiv  Detail & Related papers  (2025-04-17T04:02:53Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Understanding Generative AI Content with Embedding Models [4.662332573448995]
  We show that deep neural networks (DNNs) implicitly engineer features by transforming their input data into hidden feature vectors called embeddings. We find empirical evidence that there is intrinsic separability between real samples and those generated by artificial intelligence (AI)
  arXiv  Detail & Related papers  (2024-08-19T22:07:05Z)
• Semantically Rich Local Dataset Generation for Explainable AI in Genomics [0.716879432974126]
  Black box deep learning models trained on genomic sequences excel at predicting the outcomes of different gene regulatory mechanisms. We propose using Genetic Programming to generate datasets by evolving perturbations in sequences that contribute to their semantic diversity.
  arXiv  Detail & Related papers  (2024-07-03T10:31:30Z)
• A novel approach to graph distinction through GENEOs and permutants [0.0]
  This paper explores the use of GENEOs for distinguishing $r$-regular graphs up to isomorphisms. Our experiments show that GENEOs offer a good compromise between efficiency and computational cost in comparing $r$-regular graphs. GENEOs could be a general-purpose approach to discriminative problems in Machine Learning.
  arXiv  Detail & Related papers  (2024-06-12T09:53:14Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Equivariant Transduction through Invariant Alignment [71.45263447328374]
  We introduce a novel group-equivariant architecture that incorporates a group-in hard alignment mechanism. We find that our network's structure allows it to develop stronger equivariant properties than existing group-equivariant approaches. We additionally find that it outperforms previous group-equivariant networks empirically on the SCAN task.
  arXiv  Detail & Related papers  (2022-09-22T11:19:45Z)
• GENEOnet: A new machine learning paradigm based on Group Equivariant Non-Expansive Operators. An application to protein pocket detection [97.5153823429076]
  We introduce a new computational paradigm based on Group Equivariant Non-Expansive Operators. We test our method, called GENEOnet, on a key problem in drug design: detecting pockets on the surface of proteins that can host.
  arXiv  Detail & Related papers  (2022-01-31T11:14:51Z)
• Parsimonious neural networks learn interpretable physical laws [77.34726150561087]
  We propose parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony. The power and versatility of the approach is demonstrated by developing models for classical mechanics and to predict the melting temperature of materials from fundamental properties.
  arXiv  Detail & Related papers  (2020-05-08T16:15:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.