no code implementations • 10 Oct 2023 • Minwook Kim, Juseong Kim, Ki Beom Kim, Giltae Song
In this regard, we propose Cluster-Aware Self-Training (CAST) for tabular data, which enhances existing self-training algorithms at a negligible cost without significant modifications.
no code implementations • 27 Feb 2023 • Minwook Kim, Juseong Kim, Giltae Song
Recent progress in semi- and self-supervised learning has caused a rift in the long-held belief about the need for an enormous amount of labeled data for machine learning and the irrelevancy of unlabeled data.
1 code implementation • 29 Sep 2021 • Juseong Kim, Jinsun Park, Giltae Song
The proposed SALT consists of two blocks: Transformers and linear layers blocks that take advantage of shared attention matrices.