oversmoothing
A phenomenon in neural networks, particularly in graph neural networks, where the representations of different nodes become indistinguishable after several layers of processing.
- A CLT for Polynomial GNNs on Community-Based Graphs
- A Signed Graph Approach to Understanding and Mitigating Oversmoothing
- Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
- Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
- DiffLiG: Diffusion-enhanced Liquid Graph with Attention Propagation for Grid-to-Station Precipitation Correction
- Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
- Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models