Research map / Graph learning / Graph self-supervised learning
Fast Semi-Supervised Learning on Large Graphs: An Improved Green-Function Method
Feiping Nie, Yitao Song, Wei Chang, Rong Wang, Xuelong Li
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 Gauss Elimination solver to improved Green-function method | GF · USPS | time (s): 140.86 -> 7.18 | Improved |
| add Gauss Elimination solver | GF · USPS | accuracy (%): 91.61 -> 91.61 | No clear effect |
| use Anchored Graphs instead of full graph | GF · CsMap | time (s): 211.88 -> 0.87 | Improved |
| use Anchored Graphs instead of full graph | GF · CsMap | accuracy (%): 54.70 -> 59.63 | Improved |
| use Anchored Graphs instead of full graph | GF · USPS | accuracy (%): 91.61 -> 89.69 | Hurt |
| use Anchored Graphs instead of full graph | GF(G) · Swarm | accuracy (%): 86.31 -> 96.58 | Improved |
| add Anchored Graphs on small dataset | GF · Balance | time (s): 0.13 -> 0.26 | Hurt |
| add perturbation mu to non-fully connected graph (ablation) | GF · Two-Ring toy dataset | classification quality | Improved |
| use label margin rule instead of LLGC fitting constraint | LLGC · Balance | label margin LM_l: 1.678 -> 13.2357 | Improved |
| use GF(A) instead of RbfSVM on MNIST | supervised baseline · MNIST | accuracy (%): 76.07 -> 86.30 | Improved |
| increase number of anchors (ablation) | GF(A) · anchor study | accuracy | Mixed |
| use GF(A) instead of LLGC on USPS | LLGC · USPS | accuracy (%): 91.14 -> 89.69 | Hurt |
Closest papers by meaning
- Large-Scale Graph-Based Semi-Supervised Learning via Tree Laplacian Solver (AAAI 2016 · similarity 0.91)
- Graph Random Neural Networks for Semi-Supervised Learning on Graphs (NeurIPS 2020 · similarity 0.89)
- Graph Stochastic Neural Networks for Semi-supervised Learning (NeurIPS 2020 · similarity 0.89)
- Data driven semi-supervised learning (NeurIPS 2021 · similarity 0.89)
- Continuous Partitioning for Graph-Based Semi-Supervised Learning (NeurIPS 2024 · similarity 0.88)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.86)
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.
