Research map / Graph learning / GNN architectures
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
Vignesh Kothapalli, Tom Tirer, Joan Bruna
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use trained GNN layers instead of projected power iteration on NL | random-feature classifier · SSBM test graphs | avg test overlap: 0.04 -> 1 | Improved |
| use trained GNN layers instead of projected power iteration on BH | random-feature classifier · SSBM test graphs | avg test overlap: 0.15 -> 1 | Improved |
| train GNN until zero training error | GNN psi_F and psi_F' · SSBM training graphs | NC1 within-class variability | Improved |
| GNN versus plain DNN on instance-wise data | GNN penultimate features · SSBM | NC1 level | Hurt |
| remove W1 (psi_F' vs psi_F) (ablation) | GNN · SSBM test graphs | depthwise rate of NC1 decrease | Improved |
Closest papers by meaning
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.89)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.89)
- Almost Surely Asymptotically Constant Graph Neural Networks (NeurIPS 2024 · similarity 0.88)
- On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning (NeurIPS 2025 · similarity 0.88)
- Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective (ICML 2024 · similarity 0.88)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
