AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Interpretable Graph-Based Semi-Supervised Learning via Flows

Raif Rustamov, James Klosowski

AAAI 2018 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use flow-based prediction instead of Harmonic FunctionsFlow · MNIST 3vs8misclassification rate (%): 8.5±2.4 -> 6.2±1.6Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · MNIST 4vs9misclassification rate (%): 22.3±8.2 -> 9.6±2.7Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · AUT-AVNmisclassification rate (%): 27.9±13.7 -> 14.6±2.7Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · CCATmisclassification rate (%): 33.3±8.5 -> 22.3±3.2Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · GCATmisclassification rate (%): 20.0±11.6 -> 10.0±1.7Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · PCMACmisclassification rate (%): 30.6±11.2 -> 18.2±3.3Improved
Use flow-based prediction instead of Harmonic FunctionsFlow · REAL-SIMmisclassification rate (%): 31.5±12.1 -> 17.6±3.3Improved
Increase the sparsity parameter from λ=0.025 to λ=0.2 (ablation)Flow · MNIST 3vs8misclassification rate (%): 5.8±1.6 -> 6.7±1.4Hurt
Increase the sparsity parameter from λ=0.025 to λ=0.2 (ablation)Flow · MNIST 4vs9misclassification rate (%): 9.4±2.8 -> 10.3±2.7Hurt
Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation)Flow · AUT-AVNmisclassification rate (%): 14.0±2.6 -> 16.3±2.3Hurt
Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation)Flow · CCATmisclassification rate (%): 21.9±3.0 -> 23.2±2.5Hurt
Increase the sparsity parameter from λ=0.025 to λ=0.1 (ablation)Flow · GCATmisclassification rate (%): 9.9±1.6 -> 12.4±1.8Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy