Confident Sinkhorn Allocation for Pseudo-Labeling

Vu Nguyen, Sachin Farfade, Anton van den Hengel

Keywords: pseudo-labeling, semi-supervised learning, tabular data

TL;DR: a new pseudo-labeling method for semi-supervised learning without domain knowledge

Abstract:

Semi-supervised learning is a critical tool in reducing machine learning’s dependence on labeled data. It has been successfully applied to structure data, such as image and language data, by exploiting the inherent spatial and semantic structure therein with pretrained models or data augmentation. Some of these methods are no longer applicable for the data where domain structures are not available because the pretrained models or data augmentation can not be used.

Due to simplicity, existing pseudo-labeling (PL) methods can be widely used without any domain assumption, but are vulnerable to noise samples and to greedy assignments given a predefined threshold which is typically unknown. This paper addresses this problem by proposing a Confident Sinkhorn Allocation (CSA), which assigns labels to only samples with high confidence scores and learns the best label allocation via optimal transport. CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/confident-sinkhorn-allocation-for-pseudo/code)