Research map / Graph learning / GNN architectures
Implicit Graph 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 IGNN instead of GIN | Graph classification · MUTAG | accuracy: 89.0 \pm 6.0 -> 89.3\pm6.7 | Helped |
| Use IGNN instead of GCN | Graph classification · PTC | accuracy: 64.2 \pm 4.3 -> 70.1\pm5.6 | Helped |
| Use IGNN instead of FDGNN | Graph classification · COX2 | accuracy: 83.3 \pm 2.9 -> 86.9\pm4.0 | Helped |
| Use IGNN instead of FDGNN | Graph classification · PROTEINS | accuracy: 76.8 \pm 2.9 -> 77.7\pm3.4 | Helped |
| Use IGNN instead of WL | Graph classification · NCI1 | accuracy: 84.5 \pm 0.5 -> 80.5\pm1.9 | Hurt |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · ACM | Micro-F1: 89.8 -> 90.5 | Helped |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · ACM | Macro-F1: 89.8 -> 90.6 | Helped |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · IMDB | Micro-F1: 64.8 -> 65.5 | Helped |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · IMDB | Macro-F1: 64.8 -> 65.5 | Helped |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · DBLP | Micro-F1: 76.6 -> 73.8 | Hurt |
| Use heterogeneous IGNN instead of DMGI | Heterogeneous node classification · DBLP | Macro-F1: 77.1 -> 75.1 | Hurt |
Closest papers by meaning
- Implicit Graph Neural Networks: A Monotone Operator Viewpoint (ICML 2023 · similarity 0.93)
- Scalable and Effective Implicit Graph Neural Networks on Large Graphs (ICLR 2024 · similarity 0.91)
- Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth (ICML 2021 · similarity 0.89)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.87)
- Implicit Subgraph Neural Network (ICML 2025 · similarity 0.87)
- Forward Learning of Graph Neural Networks (ICLR 2024 · similarity 0.87)
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.