3 papers
cs.LG2026
Parallelizing Node-Level Explainability in Graph Neural Networks
Oscar Llorente, Jaime Boal, Eugenio F. Sánchez-Úbeda +2
Graph Neural Networks (GNNs) have demonstrated remarkable performance in a wide range of tasks, such as node classification, link prediction, and graph classification, by exploitin…
cs.LG2023
Evaluating Neighbor Explainability for Graph Neural Networks
Oscar Llorente, Rana Fawzy, Jared Keown +6
Explainability in Graph Neural Networks (GNNs) is a new field growing in the last few years. In this publication we address the problem of determining how important is each neighbo…
cs.AI2023
A matter of attitude: Focusing on positive and active gradients to boost saliency maps
Oscar Llorente, Jaime Boal, Eugenio F. Sánchez-Úbeda
Saliency maps have become one of the most widely used interpretability techniques for convolutional neural networks (CNN) due to their simplicity and the quality of the insights th…