Research map / Graph learning / GNN architectures
An End-to-End Deep Learning Architecture for Graph Classification
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 SortPooling + 1-D conv instead of summing node features (ablation) | DGCNN · IMDB-B | accuracy: 51.69 -> 70.03 | Helped |
| use SortPooling + 1-D conv instead of summing node features (ablation) | DGCNN · NCI1 | accuracy: 69.00 -> 74.44 | Helped |
| use SortPooling + 1-D conv instead of summing node features (ablation) | DGCNN · PROTEINS | accuracy: 76.26 -> 75.54 | No clear effect |
| DGCNN vs WL kernel | graph classification · NCI1 | accuracy: 84.46 -> 74.44 | Hurt |
| DGCNN vs WL kernel | graph classification · D&D | accuracy: 78.34 -> 79.37 | Helped |
| DGCNN vs PATCHY-SAN | graph classification · six datasets | accuracy | Mixed |
Closest papers by meaning
- Fast and Deep Graph Neural Networks (AAAI 2020 · similarity 0.90)
- KerGNNs: Interpretable Graph Neural Networks with Graph Kernels (AAAI 2022 · similarity 0.90)
- Learning Convolutional Neural Networks for Graphs (ICML 2016 · similarity 0.90)
- Convolutional Kernel Networks for Graph-Structured Data (ICML 2020 · similarity 0.89)
- Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017 · similarity 0.89)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · 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.