Research map / Graph learning / GNN architectures
Adaptive Graph Convolutional Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 AGCN with an adaptive graph and learned residual Laplacian instead of graphconv | Graph-level molecular prediction · Delaney solubility | RMSE: 0.4222 -> 0.3061 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of graphconv | Graph-level molecular prediction · Az-logD | RMSE: 0.7516 -> 0.7362 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of graphconv | Graph-level molecular prediction · NCI | RMSE: 0.8695 -> 0.8647 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of graphconv | Graph-level molecular prediction · Hydration-free energy | RMSE: 2.0329 -> 1.3317 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Tox21 validation | ROC-AUC: 0.7540 -> 0.7947 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Tox21 testing | ROC-AUC: 0.7481 -> 0.8016 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · ClinTox validation | ROC-AUC: 0.8303 -> 0.9267 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · ClinTox testing | ROC-AUC: 0.7573 -> 0.8678 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Sider validation | ROC-AUC: 0.6085 -> 0.6112 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Sider testing | ROC-AUC: 0.5914 -> 0.5921 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Toxcast validation | ROC-AUC: 0.6914 -> 0.7227 | Helped |
| Use AGCN with an adaptive graph and learned residual Laplacian instead of GCN | Molecular classification · Toxcast testing | ROC-AUC: 0.6739 -> 0.7033 | Helped |
Closest papers by meaning
- Learning Convolutional Neural Networks for Graphs (ICML 2016 · similarity 0.91)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.90)
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NeurIPS 2016 · similarity 0.90)
- Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017 · similarity 0.90)
- Simplifying Graph Convolutional Networks (ICML 2019 · similarity 0.90)
- Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks (NeurIPS 2019 · similarity 0.89)
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.