Research map / Graph learning / GNN architectures
A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
Guy Bar-Shalom, Ami Tavory, Itay Evron, Maya Bechler-Speicher, Ido Guy, Haggai Maron
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 bidirectional message passing (ablation) | WS-KAN · INR classification CIFAR-10 | accuracy: 10.0 -> 42.2 | Improved |
| add bidirectional message passing (ablation) | WS-KAN · INR classification F-MNIST | accuracy: 83.4 -> 84.6 | Improved |
| add bidirectional message passing (ablation) | WS-KAN · Accuracy prediction MNIST | MSE (x10^3): 4.03 -> 3.29 | Improved |
| add bidirectional message passing (ablation) | WS-KAN · Accuracy prediction K-MNIST | MSE (x10^3): 1.50 -> 1.45 | No clear effect |
| add bidirectional message passing (ablation) | WS-KAN · Pruning mask prediction K-MNIST | ROC-AUC (%): 97.11 -> 99.46 | Improved |
| add positional encoding (ablation) | WS-KAN · INR classification CIFAR-10 | accuracy: 46.1 -> 42.2 | Hurt |
| add positional encoding (ablation) | WS-KAN · INR classification MNIST | accuracy: 94.3 -> 94.3 | No clear effect |
| add positional encoding (ablation) | WS-KAN · Accuracy prediction MNIST | MSE (x10^3): 2.53 -> 3.29 | Hurt |
| add positional encoding (ablation) | WS-KAN · Pruning mask prediction K-MNIST | accuracy (%): 96.28 -> 97.72 | Improved |
| add permutation augmentation to MLP on flattened KAN parameters | MLP · INR classification MNIST | accuracy: 34.1 -> 62.7 | Improved |
| add KAN alignment preprocessing to MLP | MLP · INR classification MNIST | accuracy: 34.1 -> 81.0 | Improved |
| replace DeepSets over edges with the KAN-graph GNN (WS-KAN) | DS · INR classification MNIST | accuracy: 59.1 -> 94.3 | Improved |
Closest papers by meaning
- KAN: Kolmogorov–Arnold Networks (ICLR 2025 · similarity 0.91)
- On the expressiveness and spectral bias of KANs (ICLR 2025 · similarity 0.89)
- Incorporating Arbitrary Matrix Group Equivariance into KANs (ICML 2025 · similarity 0.88)
- Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks (ICLR 2025 · similarity 0.87)
- Graph Metanetworks for Processing Diverse Neural Architectures (ICLR 2024 · similarity 0.87)
- REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS (ICLR 2025 · 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.
