mlsanityData to 7 Oct 2026

Compensation Learning

arXiv 2107.11921 ↗First posted 26 Jul 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Weighting strategy prevails in machine learning. For example, a common approach in robust machine learning is to exert lower weights on samples which are likely to be noisy or quite hard. This study reveals another undiscovered strategy, namely, compensating. Various incarnations of compensating have been utilized but it has not been explicitly revealed. Learning with compensating is called compensation learning and a systematic taxonomy is constructed for it in this study. In our taxonomy, compensation learning is divided on the basis of the compensation targets, directions, inference manners, and granularity levels. Many existing learning algorithms including some classical ones can be viewed or understood at least partially as compensation techniques. Furthermore, a family of new learning algorithms can be obtained by plugging the compensation learning into existing learning algorithms. Specifically, two concrete new learning algorithms are proposed for robust machine learning. Extensive experiments on image classification and text sentiment analysis verify the effectiveness of the two new algorithms. Compensation learning can also be used in other various learning scenarios, such as imbalance learning, clustering, regression, and so on.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

33 of 62 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  8. 2016Universal adversarial perturbationscited by 774
  9. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  10. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  11. 2020Long-tail learning via logit adjustmentcited by 605
  12. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
21 more
  1. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  2. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  3. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  4. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  5. 2018Learning to Learn from Noisy Labeled Datacited by 160
  6. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  7. 2019Deep Self-Learning From Noisy Labelscited by 122
  8. 2020A Survey of Label-noise Representation Learning: Past, Present and Futurecited by 121
  9. 2018Gradient Harmonized Single-stage Detectorcited by 114
  10. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  11. 2020When Do Curricula Work?cited by 105
  12. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  13. 2020Delving Deep into Label Smoothingcited by 94
  14. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  15. 2018Universal Adversarial Trainingcited by 85
  16. 2017Deep Learning from Noisy Image Labels with Quality Embeddingcited by 46
  17. 2020ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networkscited by 33
  18. 2017Linear Regression with Sparsely Permuted Datacited by 18
  19. 2019A Two-Stage Approach to Few-Shot Learning for Image Recognitioncited by 18
  20. 2021Universal Adversarial Training with Class-Wise Perturbationscited by 13
  21. 2020Semantics-Preserving Adversarial Trainingcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Data Optimization in Deep Learning: A Surveycited by 6
  2. 2023Compensation Learning in Semantic Segmentationcited by 5