Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

By Shervin Khalafi · Paper · cs.LG

Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph transformers have recently shown promise in denoising graphs. However, our principled understanding of attention-based graph deno

Cs.lg

View original

HomeResourceLoading…