Research map / Graph learning / Graph self-supervised learning
Interpretable Graph-Based Semi-Supervised Learning via Flows
Raif Rustamov, James Klosowski
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 |
|---|---|---|---|
| Use flow-based prediction instead of Harmonic Functions | Flow · MNIST 3vs8 | misclassification rate (%): 8.5±2.4 -> 6.2±1.6 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · MNIST 4vs9 | misclassification rate (%): 22.3±8.2 -> 9.6±2.7 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · AUT-AVN | misclassification rate (%): 27.9±13.7 -> 14.6±2.7 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · CCAT | misclassification rate (%): 33.3±8.5 -> 22.3±3.2 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · GCAT | misclassification rate (%): 20.0±11.6 -> 10.0±1.7 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · PCMAC | misclassification rate (%): 30.6±11.2 -> 18.2±3.3 | Improved |
| Use flow-based prediction instead of Harmonic Functions | Flow · REAL-SIM | misclassification rate (%): 31.5±12.1 -> 17.6±3.3 | Improved |
| Increase the sparsity parameter from λ=0.025 to λ=0.2 (ablation) | Flow · MNIST 3vs8 | misclassification rate (%): 5.8±1.6 -> 6.7±1.4 | Hurt |
| Increase the sparsity parameter from λ=0.025 to λ=0.2 (ablation) | Flow · MNIST 4vs9 | misclassification rate (%): 9.4±2.8 -> 10.3±2.7 | Hurt |
| Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation) | Flow · AUT-AVN | misclassification rate (%): 14.0±2.6 -> 16.3±2.3 | Hurt |
| Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation) | Flow · CCAT | misclassification rate (%): 21.9±3.0 -> 23.2±2.5 | Hurt |
| Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation) | Flow · GCAT | misclassification rate (%): 9.9±1.6 -> 12.4±1.8 | Hurt |
Closest papers by meaning
- Large-Scale Graph-Based Semi-Supervised Learning via Tree Laplacian Solver (AAAI 2016 · similarity 0.88)
- Label Efficient Semi-Supervised Learning via Graph Filtering (CVPR 2019 · similarity 0.88)
- Data driven semi-supervised learning (NeurIPS 2021 · similarity 0.87)
- A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019 · similarity 0.87)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.86)
- From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks (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.
