Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags
Not on the map. Why?
Abstract (arXiv)
Learning from label proportions (LLP) is a kind of weakly supervised learning that trains an instance-level classifier from label proportions of bags, which consist of sets of instances without using instance labels. A challenge in LLP arises when the number of instances in a bag (bag size) is numerous, making the traditional LLP methods difficult due to GPU memory limitations. This study aims to develop an LLP method capable of learning from bags with large sizes. In our method, smaller bags (mini-bags) are generated by sampling instances from large-sized bags (original bags), and these mini-bags are used in place of the original bags. However, the proportion of a mini-bag is unknown and differs from that of the original bag, leading to overfitting. To address this issue, we propose a perturbation method for the proportion labels of sampled mini-bags to mitigate overfitting to noisy label proportions. This perturbation is added based on the multivariate hypergeometric distribution, which is statistically modeled. Additionally, loss weighting is implemented to reduce the negative impact of proportions sampled from the tail of the distribution. Experimental results demonstrate that the proportion label perturbation and loss weighting achieve classification accuracy comparable to that obtained without sampling. Our codes are available at https://github.com/stainlessnight/LLP-LargeBags.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 26 Aug 2024.
Builds on
21 of 36 references.
References · 21
- 2016Understanding deep learning requires rethinking generalizationcited by 1,657
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
- 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
- 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
- 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
- 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
- 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
- 2015Webly Supervised Learning of Convolutional Networkscited by 95
- 2014On Learning from Label Proportionscited by 38
- 2019Learning from Label Proportions with Consistency Regularizationcited by 34
- 2019Deep multi-class learning from label proportionscited by 33
9 more
- 2022Learning from Label Proportions by Learning with Label Noisecited by 30
- 2017Co-training for Demographic Classification Using Deep Learning from Label Proportionscited by 28
- 2019Learning from Label Proportions with Generative Adversarial Networkscited by 25
- 2021Two-stage Training for Learning from Label Proportionscited by 19
- 2020Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathologycited by 12
- 2023Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimizationcited by 9
- 2023MixBag: Bag-Level Data Augmentation for Learning from Label Proportionscited by 8
- 2024Learning from Partial Label Proportions for Whole Slide Image Segmentationcited by 6
- 2024Proportion Estimation by Masked Learning from Label Proportioncited by 3
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.