SEAL: Simultaneous Label Hierarchy Exploration And Learning

Zhiquan Tan, Zihao Wang, Yifan Zhang

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: semi-supervised learning, image classification, optimal transport

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We Introduce SEAL, a novel semi-supervised learning algorithm that exploits the label hierarchy during training, achieving state-of-the-art on several benchmarks..

Abstract: Label hierarchy is an important source of external knowledge that can enhance classification performance. However, most existing methods rely on predefined label hierarchies that may not match the data distribution. To address this issue, we propose Simultaneous label hierarchy Exploration And Learning (SEAL), a new framework that explores the label hierarchy by augmenting the observed labels with latent labels that follow a prior hierarchical structure. Our approach uses a 1-Wasserstein metric over the tree metric space as an objective function, which enables us to simultaneously learn a data-driven label hierarchy and perform (semi-)supervised learning. We evaluate our method on several datasets and show that it achieves superior results in both supervised and semi-supervised scenarios.

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.

Submission Number: 1232