mlsanityData to 7 Oct 2026

Learning from Label Proportions by Learning with Label Noise

arXiv 2203.02496 ↗First posted 4 Mar 2022cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. The task is to learn a classifier to predict the individual labels of future individual instances. Prior work on LLP for multi-class data has yet to develop a theoretically grounded algorithm. In this work, we provide a theoretically grounded approach to LLP based on a reduction to learning with label noise, using the forward correction (FC) loss of citetPatrini2017MakingDN. We establish an excess risk bound and generalization error analysis for our approach, while also extending the theory of the FC loss which may be of independent interest. Our approach demonstrates improved empirical performance in deep learning scenarios across multiple datasets and architectures, compared to the leading existing methods.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 17 of its 61 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

17 of 61 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Wide Residual Networkscited by 3,057
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  6. 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
  7. 2016A vector-contraction inequality for Rademacher complexitiescited by 141
  8. 2014On Learning from Label Proportionscited by 38
  9. 2019Learning from Label Proportions with Consistency Regularizationcited by 34
  10. 2019Deep multi-class learning from label proportionscited by 33
  11. 2017Co-training for Demographic Classification Using Deep Learning from Label Proportionscited by 28
  12. 2019Learning from Label Proportions with Generative Adversarial Networkscited by 25
5 more
  1. 2017Weakly Supervised Classification in High Energy Physicscited by 21
  2. 2021Two-stage Training for Learning from Label Proportionscited by 19
  3. 2018Deep Learning from Label Proportions for Emphysema Quantificationcited by 13
  4. 2021Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classificationcited by 12
  5. 2018Label Propagation for Learning with Label Proportionscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 13; 2025: 6; 2026: 3.

30 papers.

Sort:

  1. 2023Easy Learning from Label Proportionscited by 20
  2. 2024Enhanced H-Consistency Boundscited by 18
  3. 2024In-Context Example Ordering Guided by Label Distributionscited by 12
  4. 2022Unsupervised Learning under Latent Label Shiftcited by 9
  5. 2024Label Noise: Ignorance Is Blisscited by 8
  6. 2023Evaluating AI systems under uncertain ground truth: a case study in dermatologycited by 7
  7. 2023Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagationcited by 7
  8. 2024A General Framework for Learning from Weak Supervisioncited by 7
  9. 2023LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportionscited by 5
  10. 2024Optimistic Rates for Learning from Label Proportionscited by 5
  11. 2025Nearly Optimal Sample Complexity for Learning with Label Proportionscited by 4
  12. 2024A Practical Theory of Generalization in Selectivity Learningcited by 3
18 more
  1. 2022Learning from Label Proportions with Instance-wise Consistencycited by 2
  2. 2024PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responsescited by 2
  3. 2024Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bagscited by 2
  4. 2024Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportionscited by 2
  5. 2023Kernel Density Matrices for Probabilistic Deep Learningcited by 1
  6. 2023Label Differential Privacy via Aggregationcited by 1
  7. 2025Meta-Statistical Learning: Supervised Learning of Statistical Estimatorscited by 1
  8. 2025Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labelingcited by 1
  9. 2025Optimal Learning from Label Proportions with General Loss Functionscited by 1
  10. 2024FRACTAL: Fine-Grained Scoring from Aggregate Text Labelscited by 0
  11. 2024Class-aware and Augmentation-free Contrastive Learning from Label Proportioncited by 0
  12. 2024Weak to Strong Learning from Aggregate Labelscited by 0
  13. 2024Learning from Label Proportions and Covariate-shifted Instancescited by 0
  14. 2025Neuro-symbolic Weak Supervision: Theory and Semanticscited by 0
  15. 2025Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportionscited by 0
  16. 2026Statistical Learning from Attribution Setscited by 0
  17. 2026FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learningcited by 0
  18. 2026Learning from Label Proportions with Dual-proportion Constraintscited by 0