Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Nazari, Philipp"'
Deep Graph Neural Networks struggle with oversmoothing. This paper introduces a novel, physics-inspired GNN model designed to mitigate this issue. Our approach integrates with existing GNN architectures, introducing an entropy-aware message passing t
Externí odkaz:
http://arxiv.org/abs/2403.04636
Visualization is a crucial step in exploratory data analysis. One possible approach is to train an autoencoder with low-dimensional latent space. Large network depth and width can help unfolding the data. However, such expressive networks can achieve
Externí odkaz:
http://arxiv.org/abs/2306.17638