Partial Optimal Transport for Open-set Semi-supervised Learning

Yilong Ren, Chuanwen Feng, Xike Xie, S Kevin ZhouOpenReview 2024 · Submission to ICLR 2024 · Rejected · OpenReview

Abstract

Semi-supervised learning (SSL) is a machine learning paradigm that leverages both labeled and unlabeled data to improve the performance of learning tasks. However, SSL methods make an assumption that the label spaces of labeled and unlabeled data are identical, which may not hold in open-world applications, where the unlabeled data may contain novel categories that were not present in the labeled training data, essentially outliers. This paper tackles open-set semi-supervised learning (OSSL), where detecting these outliers, or out-of-distribution (OOD) data, is critical. In particular, we model the OOD detection problem in OSSL as a partial optimal transport (POT) problem. With the theory of POT, we devise a mass score function (MSF) to measure the likelihood of a sample being an outlier during training. Then, a novel OOD loss is proposed, which allows to adapt the off-the-shelf SSL methods with POT into OSSL settings in an end-to-end training manner. Furthermore, we conduct extensive experiments on multiple datasets and OSSL configurations, demonstrating that our method consistently achieves superior or competitive results compared to existing approaches.
BibTeX
@misc{ren2024partial,
  author = {Yilong Ren and Chuanwen Feng and Xike Xie and S Kevin Zhou},
  title = {{Partial Optimal Transport for Open-set Semi-supervised Learning}},
  year = {2024},
  url = {https://openreview.net/forum?id=3WB5hT27zf},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2024},
}

Loading related content...

Figure