Book
Open access
Aug 2026
Spectral Gap-Driven Coarsening for Dynamic Graph Neural Networks
Experimental results demonstrate that the coarsening technique significantly accelerates dynamic GNN training and inference without compromising predictive performance, offering a practical path toward scalable dynamic graph learning.
Hieu Vu, Rares-Mihail Neagu, Bijaya Adhikari
· Proceedings of the 32nd ACM... · 0 citations