mlsanityData to 7 Oct 2026

Label Propagation with Weak Supervision

arXiv 2210.03594 ↗First posted 7 Oct 2022cs.LG stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In this paper, we introduce a novel analysis of the classical label propagation algorithm (LPA) (Zhu & Ghahramani, 2002) that moreover takes advantage of useful prior information, specifically probabilistic hypothesized labels on the unlabeled data. We provide an error bound that exploits both the local geometric properties of the underlying graph and the quality of the prior information. We also propose a framework to incorporate multiple sources of noisy information. In particular, we consider the setting of weak supervision, where our sources of information are weak labelers. We demonstrate the ability of our approach on multiple benchmark weakly supervised classification tasks, showing improvements upon existing semi-supervised and weakly supervised methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

33 of 52 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  9. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  10. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 370
  11. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  12. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
21 more
  1. 2016Data Programming: Creating Large Training Sets, Quicklycited by 246
  2. 2014Learning with Pseudo-Ensemblescited by 241
  3. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  4. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
  5. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  6. 2020Algorithms with Predictionscited by 152
  7. 2018Training Complex Models with Multi-Task Weak Supervisioncited by 106
  8. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  9. 2020Unifying Graph Convolutional Neural Networks and Label Propagationcited by 98
  10. 2020Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methodscited by 98
  11. 2021WRENCH: A Comprehensive Benchmark for Weak Supervisioncited by 95
  12. 2020Learning from Rules Generalizing Labeled Exemplarscited by 59
  13. 2020On the Equivalence of Decoupled Graph Convolution Network and Label Propagationcited by 49
  14. 2021A Theory of Label Propagation for Subpopulation Shiftcited by 48
  15. 2018Deep Metric Transfer for Label Propagation with Limited Annotated Datacited by 33
  16. 2022Learning Predictions for Algorithms with Predictionscited by 25
  17. 2021DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samplescited by 18
  18. 2022Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervisioncited by 18
  19. 2020Constrained Labeling for Weakly Supervised Learningcited by 10
  20. 2013Scaling Graph-based Semi Supervised Learning to Large Number of Labels Using Count-Min Sketchcited by 6
  21. 2022Data Consistency for Weakly Supervised Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 3; 2026: 1.

9 papers.

  1. 2024Theoretical Analysis of Weak-to-Strong Generalizationcited by 46
  2. 2023Learning with Explanation Constraintscited by 8
  3. 2023Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagationcited by 7
  4. 2023Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classificationcited by 3
  5. 2023How Graph Neural Networks Learn: Lessons from Training Dynamicscited by 3
  6. 2025Analyzing Similarity Metrics for Data Selection for Language Model Pretrainingcited by 3
  7. 2025Learning from Interval Targetscited by 1
  8. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  9. 2026Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularizationcited by 0