Research map / Graph learning / GNN architectures
Motif-Matching Based Subgraph-Level Attentional Convolutional Network for Graph Classification
Hao Peng, Jianxin Li, Qiran Gong, Yuanxin Ning, Senzhang Wang, Lifang He
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 |
|---|---|---|---|
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · MUTAG | accuracy (%): 92.78 -> 93.89 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · PTC | accuracy (%): 70.30 -> 71.76 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · PROTEINS | accuracy (%): 78.19 -> 79.35 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · D&D | accuracy (%): 81.37 -> 81.48 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · NCI1 | accuracy (%): 80.91 -> 81.77 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · IMDB-B | accuracy (%): 75.10 -> 77.20 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · IMDB-M | accuracy (%): 52.19 -> 53.77 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · RE-B | accuracy (%): 88.06 -> 89.44 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · RE-M-5K | accuracy (%): 55.62 -> 56.18 | Improved |
| add subgraph-level self-attention to M-GCNN (ablation) | M-GCNN · RE-M-12K | accuracy (%): 47.35 -> 48.14 | Improved |
| MA-GCNN vs Weisfeiler-Lehman kernel | graph classification · NCI1 | accuracy (%): 84.55 -> 81.77 | Hurt |
| add motif-matching normalization (M-GCNN) vs PSCN | graph CNN · MUTAG | accuracy (%): 92.63 -> 92.78 | Improved |
Closest papers by meaning
- Graph Attention Networks (ICLR 2018 · similarity 0.88)
- Graph-Context Attention Networks for Size-Varied Deep Graph Matching (CVPR 2022 · similarity 0.87)
- DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification (AAAI 2025 · similarity 0.86)
- Subgraph Invariant Learning Towards Large-Scale Graph Node Classification (AAAI 2025 · similarity 0.86)
- SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning (AAAI 2025 · similarity 0.86)
- Pre-Training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck (AAAI 2025 · similarity 0.85)
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.
