mlsanityData to 7 Oct 2026

Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates

arXiv 2006.11184 ↗First posted 19 Jun 2020cs.LG cs.CV cs.NAcited by 49

Not on the map. Why?

Abstract (arXiv)

We propose a new framework, called Poisson learning, for graph based semi-supervised learning at very low label rates. Poisson learning is motivated by the need to address the degeneracy of Laplacian semi-supervised learning in this regime. The method replaces the assignment of label values at training points with the placement of sources and sinks, and solves the resulting Poisson equation on the graph. The outcomes are provably more stable and informative than those of Laplacian learning. Poisson learning is efficient and simple to implement, and we present numerical experiments showing the method is superior to other recent approaches to semi-supervised learning at low label rates on MNIST, FashionMNIST, and Cifar-10. We also propose a graph-cut enhancement of Poisson learning, called Poisson MBO, that gives higher accuracy and can incorporate prior knowledge of relative class sizes.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 7; 2024: 11; 2025: 7; 2026: 8.

49 papers.

Sort:

  1. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  2. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  3. 2021GraphHop: An Enhanced Label Propagation Method for Node Classificationcited by 15
  4. 2023From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approachcited by 15
  5. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  6. 2021Uniform Convergence Rates for Lipschitz Learning on Graphscited by 9
  7. 2021Model-Change Active Learning in Graph-Based Semi-Supervised Learningcited by 8
  8. 2022Hamilton-Jacobi equations on graphs with applications to semi-supervised learning and data depthcited by 7
  9. 2022Graph-based Active Learning for Semi-supervised Classification of SAR Datacited by 7
  10. 2023Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clusteringcited by 7
  11. 2022Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learningcited by 6
  12. 2023Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumptioncited by 6
37 more
  1. 2021PoissonSeg: Semi-Supervised Few-Shot Medical Image Segmentation via Poisson Learningcited by 4
  2. 2023Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasetscited by 4
  3. 2024A mean curvature flow arising in adversarial trainingcited by 4
  4. 2021PPGN: Physics-Preserved Graph Networks for Real-Time Fault Location in Distribution Systems with Limited Observation and Labelscited by 3
  5. 2022Label Efficient Regularization and Propagation for Graph Node Classificationcited by 3
  6. 2024Consistency of semi-supervised learning, stochastic tug-of-war games, and the p-Laplaciancited by 3
  7. 2022Joint reconstruction-segmentation on graphscited by 2
  8. 2023Persistent Laplacian-enhanced Algorithm for Scarcely Labeled Data Classificationcited by 2
  9. 2023Multi-class Graph Clustering via Approximated Effective p-Resistancecited by 2
  10. 2024Improved Graph-based semi-supervised learning Schemescited by 2
  11. 2021Dual GNNs: Graph Neural Network Learning with Limited Supervisioncited by 1
  12. 2022Eikonal depth: an optimal control approach to statistical depthscited by 1
  13. 2022Digital Fingerprinting of Microstructurescited by 1
  14. 2024Hypergraph p-Laplacian regularization on point clouds for data interpolationcited by 1
  15. 2024MALADY: Multiclass Active Learning with Auction Dynamics on Graphscited by 1
  16. 2024Graph-Based Semi-Supervised Segregated Lipschitz Learningcited by 1
  17. 2025Advancing Local Clustering on Graphs via Compressive Sensing: Semi-supervised and Unsupervised Methodscited by 1
  18. 2025Higher-Order Regularization Learning on Hypergraphscited by 1
  19. 2026High-dimensional Semi-supervised Classification via the Fermat Distancecited by 1
  20. 2022Semi-supervised Learning on Large Graphs: is Poisson Learning a Game-Changer?cited by 0
  21. 2024Why the Metric Backbone Preserves Community Structurecited by 0
  22. 2024Interface Laplace Learning: Learnable Interface Term Helps Semi-Supervised Learningcited by 0
  23. 2024A Laplacian-based Quantum Graph Neural Network for Semi-Supervised Learningcited by 0
  24. 2024Neural Networks for Threshold Dynamics Reconstructioncited by 0
  25. 2024Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphscited by 0
  26. 2025Constraint Multi-class Positive and Unlabeled Learning for Distantly Supervised Named Entity Recognitioncited by 0
  27. 2025Sparse Techniques for Regression in Deep Gaussian Processescited by 0
  28. 2025Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methodscited by 0
  29. 2025Topology-Aware Active Learning on Graphscited by 0
  30. 2025ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Datacited by 0
  31. 2026AI-enabled Satellite Edge Computing: A Single-Pixel Feature based Shallow Classification Model for Hyperspectral Imagingcited by 0
  32. 2026Graph-based Semi-Supervised Learning via Maximum Discriminationcited by 0
  33. 2026STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecastingcited by 0
  34. 2026A Near-Linear-Time Solver for Graph p-Laplacian Semi-Supervised Learning via Continuation in pcited by 0
  35. 2026Fermat Active Laplace Learning for Semi-Supervised Hyperspectral Image Classificationcited by 0
  36. 2026A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Datacited by 0
  37. 2026Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learningcited by 0