Pierre Vandergheynst

3 papers EPFL

• Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings
• On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
• Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks