GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
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 …
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
Malicious websites present a substantial threat to the security and privacy of individuals
using the internet. Traditional approaches for identifying these malicious sites have …
using the internet. Traditional approaches for identifying these malicious sites have …
L2XGNN: learning to explain graph neural networks
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 …
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
Regulators, researchers, and practitioners recognize the urgency of explainability in artificial
intelligence systems, including the ones based on machine learning for graph-structured …
intelligence systems, including the ones based on machine learning for graph-structured …
Protein dynamics inform protein structure: An interdisciplinary investigation of protein crystallization propensity
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 …
and function but overlooks conformational fluctuation that is integral to protein function. We …
GNNShap: Scalable and Accurate GNN Explanation using Shapley Values
Graph neural networks (GNNs) are popular machine learning models for graphs with many
applications across scientific domains. However, GNNs are considered black box models …
applications across scientific domains. However, GNNs are considered black box models …
Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks
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 …
but they lack explainability, especially at the global level. Current research mainly utilizes …
GNNShap: Fast and Accurate GNN Explanations using Shapley Values
Graph neural networks (GNNs) are popular machine learning models for graphs with many
applications across scientific domains. However, GNNs are considered black box models …
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 …
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 …
significantly improve the motor development of affected children and reduce the emotional …