Confident Sinkhorn Allocation for Pseudo-Labeling
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: pseudo-labeling
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: a new method for pseudo-labeling with some theoretical properties
Abstract: Semi-supervised learning is a critical tool in reducing machine learning’s dependence on labeled data. It has been successfully applied to structured data, such as images and natural language, by exploiting the inherent spatial and semantic structure therein with pretrained models or data augmentation. These methods are not applicable, however, when the data does not have the appropriate structure, or
invariances. Due to their simplicity, pseudo-labeling (PL) methods can be widely used without any domain assumptions. However, PL is sensitive to a threshold and can perform poorly if wrong assignments are made due to overconfidence. This paper studies theoretically the role of uncertainty to pseudo-labeling and proposes Confident Sinkhorn Allocation (CSA), which identifies the best pseudo-label allocation via optimal transport to only samples with high confidence scores. CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning. Additionally, we propose to use the Integral Probability Metrics to extend and improve the existing PAC-Bayes bound which relies on the Kullback-Leibler (KL) divergence, for ensemble models.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: pdf
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4713
Loading