Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability

Lorenzo Bini, Marco Sorbi, Stephane Marchand-Maillet

Published: 06 Mar 2025, Last Modified: 19 Apr 2025ICLR 2025 Workshop XAI4ScienceEveryoneRevisionsBibTeXCC BY 4.0
Submission Number: 24