mlsanityData to 7 Oct 2026

Disambiguation of weak supervision with exponential convergence rates

arXiv 2102.02789 ↗First posted 4 Feb 2021cs.LG cs.AI stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Machine learning approached through supervised learning requires expensive annotation of data. This motivates weakly supervised learning, where data are annotated with incomplete yet discriminative information. In this paper, we focus on partial labelling, an instance of weak supervision where, from a given input, we are given a set of potential targets. We review a disambiguation principle to recover full supervision from weak supervision, and propose an empirical disambiguation algorithm. We prove exponential convergence rates of our algorithm under classical learnability assumptions, and we illustrate the usefulness of our method on practical examples.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 58 references that are in the map. First posted on arXiv 4 Feb 2021.

Builds on

16 of 58 references.

References · 16

  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  3. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  4. 2017Multi-task Self-Supervised Visual Learningcited by 200
  5. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  6. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  7. 2015Unsupervised Learning from Narrated Instruction Videoscited by 116
  8. 2020Missing Data Imputation using Optimal Transportcited by 99
  9. 2020A General Framework for Consistent Structured Prediction with Implicit Loss Embeddingscited by 35
  10. 2020Structured Prediction with Partial Labelling through the Infimum Losscited by 34
  11. 2016A Consistent Regularization Approach for Structured Predictioncited by 33
  12. 2019Deep multi-class learning from label proportionscited by 33
4 more
  1. 2019A Regularization Approach for Instance-Based Superset Label Learningcited by 21
  2. 2018A Structured Prediction Approach for Label Rankingcited by 18
  3. 2018Sharp Analysis of Learning with Discrete Lossescited by 13
  4. 2021Fast rates in structured predictioncited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2024Theoretical Analysis of Weak-to-Strong Generalizationcited by 46
  2. 2023Conformal Prediction with Partially Labeled Datacited by 5
  3. 2022A Case of Exponential Convergence Rates for SVMcited by 3
  4. 2022From Weakly Supervised Learning to Active Learningcited by 0