Research map / Graph learning / Graph algorithms and clustering
KONG: Kernels for ordered-neighborhood graphs
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 KONG instead of the strongest listed baseline | KONG · MUTAG | accuracy: 84.9 $\pm$ 2.1 -> 87.8 $\pm$ 0.7 | Helped |
| Use KONG instead of the strongest listed baseline | KONG · ENZYMES | accuracy: 52.9 $\pm$ 1.1 -> 50.1 $\pm$ 1.1 | Hurt |
| Use KONG instead of the strongest listed baseline | KONG · PTC | accuracy: 62.4 $\pm$ 1.2 -> 63.7 $\pm$ 0.8 | Helped |
| Use KONG instead of the strongest listed baseline | KONG · Proteins | accuracy: 71.4 $\pm$ 0.7 -> 73.0 $\pm$ 0.6 | Helped |
| Use KONG instead of the strongest listed baseline | KONG · NCI1 | accuracy: 81.4 $\pm$ 0.3 -> 76.4 $\pm$ 0.3 | Hurt |
| Use KONG instead of the strongest listed baseline | KONG · MSRC | accuracy: 92.9 $\pm$ 0.8 -> 95.2 $\pm$ 1.3 | Helped |
| Use KONG instead of the strongest listed baseline | KONG · BZR | accuracy: 85.9 $\pm$ 0.9 -> 85.1 $\pm$ 1.1 | Hurt |
| Use KONG instead of the strongest listed baseline | KONG · COX2 | accuracy: 80.7 $\pm$ 0.8 -> 81.8 $\pm$ 2.1 | Helped |
| Use KONG instead of the strongest listed baseline | KONG · DHFR | accuracy: 81.4 $\pm$ 0.6 -> 80.1 $\pm$ 0.5 | Hurt |
| Preserve neighborhood order rather than shuffle it (ablation) | KONG 2-grams · Web browsing | accuracy: 99.81 -> 99.95 | Helped |
| Preserve neighborhood order rather than shuffle it (ablation) | KONG 2-grams · MovieLens | accuracy: 67.01 -> 67.68 | Helped |
| Preserve neighborhood order rather than shuffle it (ablation) | KONG 2-grams · Dunnhumby | accuracy: 90.57 -> 90.56 | No clear effect |
Closest papers by meaning
- Graph Filtration Kernels (AAAI 2022 · similarity 0.89)
- Convolutional Kernel Networks for Graph-Structured Data (ICML 2020 · similarity 0.88)
- Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation (ICLR 2025 · similarity 0.87)
- Rethinking Kernel Methods for Node Representation Learning on Graphs (NeurIPS 2019 · similarity 0.87)
- Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification (AAAI 2024 · similarity 0.86)
- DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification (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.