Research map / Label-efficient and robust learning / Semi-supervised learning
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
Jeff Calder, Brendan Cook, Matthew Thorpe, Dejan Slepcev
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 Poisson MBO graph-cut refinement to Poisson learning | Poisson learning · MNIST, 1 label/class | accuracy: 90.2 (4.0) -> 96.5 (2.6) | Improved |
| Add Poisson MBO graph-cut refinement to Poisson learning | Poisson learning · FashionMNIST, 1 label/class | accuracy: 60.8 (4.6) -> 62.0 (5.7) | Improved |
| Add Poisson MBO graph-cut refinement to Poisson learning | Poisson learning · Cifar-10, 1 label/class | accuracy: 40.7 (5.5) -> 41.8 (6.5) | Improved |
| Subtract the estimated tail constant before making label decisions | Laplace/LP · MNIST, 1 label/class (10 labeled images total) | accuracy: 16% -> 85.9% | Improved |
| Use Poisson learning instead of Laplace/LP | Graph-based semi-supervised classification · MNIST, 1 label/class | accuracy: 16.1 (6.2) -> 90.2 (4.0) | Improved |
| Use Poisson learning instead of Laplace/LP | Graph-based semi-supervised classification · FashionMNIST, 1 label/class | accuracy: 18.4 (7.3) -> 60.8 (4.6) | Improved |
| Use Poisson learning instead of Laplace/LP | Graph-based semi-supervised classification · Cifar-10, 1 label/class | accuracy: 10.4 (1.3) -> 40.7 (5.5) | Improved |
| Vary the number of neighbors used to construct the graph | Poisson learning · Datasets tested, 5 labels/class | accuracy | No clear effect |
| Compensate for unbalanced training labels in the label decision | Poisson learning · Datasets tested, unbalanced training labels | accuracy | Improved |
Closest papers by meaning
- Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data (ICLR 2024 · similarity 0.93)
- PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning (AAAI 2021 · similarity 0.90)
- Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels (NeurIPS 2021 · similarity 0.88)
- Data driven semi-supervised learning (NeurIPS 2021 · similarity 0.88)
- Large-Scale Graph-Based Semi-Supervised Learning via Tree Laplacian Solver (AAAI 2016 · similarity 0.87)
- Continuous Partitioning for Graph-Based Semi-Supervised Learning (NeurIPS 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.
