GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules

B Armgaan, M Dalmia, S Medya… - Advances in Neural …, 2025 - proceedings.neurips.cc
Instance-level explanation of graph neural networks (GNNs) is a well-studied area. These
explainers, however, only explain an instance (eg, a graph) and fail to uncover the …

Efficient Classification of Malicious URLs: M-BERT-A Modified BERT Variant for Enhanced Semantic Understanding

B Yu, F Tang, D Ergu, R Zeng, B Ma, F Liu - IEEE Access, 2024 - ieeexplore.ieee.org
Malicious websites present a substantial threat to the security and privacy of individuals
using the internet. Traditional approaches for identifying these malicious sites have …

L2XGNN: learning to explain graph neural networks

G Serra, M Niepert - Machine learning, 2024 - Springer
Abstract Graph Neural Networks (GNNs) are a popular class of machine learning models.
Inspired by the learning to explain (L2X) paradigm, we propose l2xGnn, a framework for …

A True-to-the-model Axiomatic Benchmark for Graph-based Explainers

C Monti, P Bajardi, F Bonchi, A Panisson… - … on Machine Learning …, 2024 - openreview.net
Regulators, researchers, and practitioners recognize the urgency of explainability in artificial
intelligence systems, including the ones based on machine learning for graph-structured …

Protein dynamics inform protein structure: An interdisciplinary investigation of protein crystallization propensity

M Madani, A Tarakanova - Matter, 2024 - cell.com
The classical central paradigm of structural biology links a protein's sequence to its structure
and function but overlooks conformational fluctuation that is integral to protein function. We …

GNNShap: Scalable and Accurate GNN Explanation using Shapley Values

S Akkas, A Azad - Proceedings of the ACM on Web Conference 2024, 2024 - dl.acm.org
Graph neural networks (GNNs) are popular machine learning models for graphs with many
applications across scientific domains. However, GNNs are considered black box models …

Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks

D Köhler, S Heindorf - arxiv preprint arxiv:2405.12654, 2024 - arxiv.org
Graph Neural Networks (GNNs) are effective for node classification in graph-structured data,
but they lack explainability, especially at the global level. Current research mainly utilizes …

GNNShap: Fast and Accurate GNN Explanations using Shapley Values

S Akkas, A Azad - arxiv preprint arxiv:2401.04829, 2024 - arxiv.org
Graph neural networks (GNNs) are popular machine learning models for graphs with many
applications across scientific domains. However, GNNs are considered black box models …

Toward explainable biomedical deep learning

A Mastropietro - 2024 - iris.uniroma1.it
Deep learning has been extensively utilized in the domains of bioinformatics and
chemoinformatics, yielding compelling results. However, neural networks have …

Explaining a Deep Learning Model for Cerebral Palsy Prediction-Studying the Use of SHAP in the DeepInMotion Project

HVC Ameln, LH Sandberg - 2024 - ntnuopen.ntnu.no
Early diagnosis of cerebral palsy (CP) is crucial for timely intervention, which can
significantly improve the motor development of affected children and reduce the emotional …