People

Faculty

Research Areas
Machine Learning & Learning Theory
Assistant Professor
Sung Whan Yoon

The main research goal of our group is to develop theory-driven next-generation machine learning algorithms/architectures which tackle existing challenges of today’s artificial intelligence. Specifically, we aim to build a data-efficient, life-long learnable, generalizing to unseen data/tasks learning framework that can be trained on a decentralized data/resource environment.

[Curriculum Vitae]

● 2020-Present: Assistant Professor, Department of Electrical Engineering & Artificial Intelligence Graduate School, UNIST
● 2017-2020: Post-doctoral researcher, Department of Electrical Engineering, KAIST

[Education]

● 2017: Ph.D., in Department of Electrical Engineering, KAIST
● 2013: M.S., in Department of Electrical Engineering, KAIST
● 2011: B.S., Department of Electrical Engineering, KAIST

[Research  Keywords and Topics]

● Deep Learning Theory
● Data-efficient Learning
● Generalization
● Federated Learning
● Intelligent Communications
● Information Theory & Learning

[Publications (selected)]

● S-Y Jo, and S. W. Yoon, “POEM: Polarization of Embeddings for Domain-Invariant Representations,” 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
● J. H. Lim, and S. W. Yoon, “MetaVerSe: Federated Meta-Learning for Versatile and Secure Representations with Dynamic Margins in Embedding Space,” AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-23), 2023.
● S. W. Yoon, D-Y Kim, J. Seo, and J. Moon, “XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning,” 37th International Conference on Machine Learning (ICML), 2020.
● S. W. Yoon, J. Seo, and J. Moon, “TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning,” 36th International Conference on Machine Learning (ICML), 2019.
● J-Y Sohn, S. W. Yoon, and J. Moon, “Capacity of Clustered Distributed Storage,” IEEE Transactions on Information Theory, Jan. 2019.

[Awards/ Honors/ Memberships]

● Best Teaching Achievements Award in UNIST 2021 (one winner among all faculty members)
● Samsung AI Forum Best Poster Award, 2019
● Qualcomm Innovation Paper Award, 2015 & 2018
● IEEE International Conference on Communications (ICC) Best Paper Award for Communication Theory Symposium, 2017