Search Results for author: Taero Kim

Found 2 papers, 1 papers with code

Sufficient Invariant Learning for Distribution Shift

no code implementations • 24 Oct 2022 • Taero Kim, Sungjun Lim, Kyungwoo Song

Moreover, we propose a new algorithm, Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO), to learn sufficient invariant features across domains or groups.

Data Augmentation

Paper
Add Code

Learning Fair Representation via Distributional Contrastive Disentanglement

1 code implementation • ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2022 • Changdae Oh, Heeji Won, Junhyuk So, Taero Kim, Yewon Kim, Hosik Choi, Kyungwoo Song

We provide a new type of contrastive loss motivated by Gaussian and Student-t kernels for distributional contrastive learning with theoretical analysis.

Contrastive Learning Disentanglement +2

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.