no code implementations • 27 Feb 2024 • Ha Min Son, Moon-Hyun Kim, Tai-Myoung Chung, Chao Huang, Xin Liu
Based on this finding, we introduce two regularization terms for local training to continuously emulate IID settings: (1) variance in the dimension-wise probability distribution of the classifier and (2) hyperspherical uniformity of representations of the encoder.
no code implementations • 1 Dec 2021 • Ha Min Son, Moon Hyun Kim, Tai-Myoung Chung
Federated Learning is a widely adopted method to train neural networks over distributed data.
no code implementations • 4 Aug 2021 • Joo Hun Yoo, Ha Min Son, Hyejun Jeong, Eun-Hye Jang, Ah Young Kim, Han Young Yu, Hong Jin Jeon, Tai-Myoung Chung
While machine learning techniques are being applied to various fields for their exceptional ability to find complex relations in large datasets, the strengthening of regulations on data ownership and privacy is causing increasing difficulty in its application to medical data.