Research map / Graph learning / Graph algorithms and clustering
Neighborhood Preserving Kernels for Attributed Graphs
Asif Salim, S. S. Shiju, S. Sumitra
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 label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · BZR (graph classification) | accuracy (%): 87.13 -> 89.12 | Improved |
| add label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · DHFR (graph classification) | accuracy (%): 82.70 -> 83.98 | Improved |
| add label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · SYNTHETICnew (graph classification) | accuracy (%): 99.51 -> 99.74 | Improved |
| add label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · PROTEINS (graph classification) | accuracy (%): 71.08 -> 73.66 | Improved |
| add label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · ENZYMES (graph classification) | accuracy (%): 64.93 -> 58.10 | Hurt |
| add label-processing NPO kernel to attribute kernel NPE (NP) (ablation) | NPE · COX2 (graph classification) | accuracy (%): 82.36 -> 81.16 | Hurt |
| add attribute kernel NPE to label kernel NPO (NP) (ablation) | NPO · ENZYMES (graph classification) | accuracy (%): 45.67 -> 58.10 | Improved |
| add attribute kernel NPE to label kernel NPO (NP) (ablation) | NPO · SYNTHETICnew (graph classification) | accuracy (%): 97.81 -> 99.74 | Improved |
| use NPS (shortest-path-style) variant instead of NP | NP · DHFR (graph classification) | accuracy (%): 83.98 -> 84.16 | Improved |
| use NP kernel instead of discretization based Propagation kernel | Prop-WL · SYNTHETICnew (graph classification) | accuracy (%): 46.38 -> 99.74 | Improved |
| use NP kernel instead of discretization based Propagation kernel | Prop-WL · BZR (graph classification) | accuracy (%): 78.92 -> 89.12 | Improved |
| compute NPO alone rather than NPE or NP (ablation) | NP · Runtime ENZYMES (graph classification) | runtime: 7' 10" -> 41" | Improved |
Closest papers by meaning
- Graph Filtration Kernels (AAAI 2022 · similarity 0.90)
- Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks (NeurIPS 2024 · similarity 0.86)
- 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 0.86)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · similarity 0.85)
- Generalizing Weisfeiler-Lehman Kernels to Subgraphs (ICLR 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.
