Introduction

I’m a Ph.D. student at Machine Learning and Artificial Intelligence (MLAI) Lab in Korea Advanced Institute of Science and Technology (KAIST), under the supervision of Prof. Sung Ju Hwang. I finished the B.S. degree at UNIST in 2016 and the M.S. degree at UNIST in 2018 under the supervision of Prof. Sung Ju Hwang.

My research interests focus on:

Lifelong-able (Online) Continual Learning
On-device Federated Learning
Neural Architecture Search
Un/Semi-supervised Learning
Scalable/Efficient Deep Neural Network Models and Algorithms
Biologically Plausible Neural Networks

Publications/Preprints

Federated Semi-supervised Learning with Inter-client Consistency

Wonyong Jeong, Jaehong Yoon, Eunho Yang, and Sung Ju Hwang
Federated Learning Workshop @ International Conference on Machine Learning (ICML), 2020

Keyword: Federated Learning, Semi-supervised Learning

Scalable and Order-robust Continual Learning with Additive Parameter Decomposition

Jaehong Yoon, Saehoon Kim, Eunho Yang, and Sung Ju Hwang
International Conference on Learning Representation (ICLR), 2020

Keyword: Continual Learning, Lifelong Learning, Task-order Sensitivity

Lifelong Learning with Dynamically Expandable Networks

Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang
International Conference on Learning Representation (ICLR), 2018

Keyword: Continual Learning, Lifelong Learning, Dynamic Network Expansion

Combined Group and Exclusive Sparsity for Deep Neural Networks

Jaehong Yoon and Sung Ju Hwang
International Conference on Machine Learning (ICML), 2017

Keyword: Structured Sparsity, Network Sparsification, Efficient Deep Neural Networks

Adaptive Network Sparsification with Dependent Variational Beta-Bernoulli Dropout

Juho Lee, Saehoon Kim, Jaehong Yoon, Hae Beom Lee, Eunho Yang, and Sung Ju Hwang
Arxiv, 2018

Keyword: Bayesian Pruning, Input-dependent Sparsifcation, Efficient Deep Neural Networks

Federated Continual Learning with Weighted Inter-client Transfer

Jaehong Yoon*, Wonyong Jeong*, Giwoong Lee, Eunho Yang, and Sung Ju Hwang
Lifelong Machine Learning Workshop @ International Conference on Machine Learning (ICML), 2020

Keyword: Federated Learning, Continual Learning, Multi-client Distributed Learning

Rapid Structural Pruning of Neural Networks with Set-based Task-Adaptive Meta-Pruning

Minyoung Song, Jaehong Yoon, Eunho Yang, and Sung Ju Hwang
Arxiv, 2020

Keyword: Network Compression, Efficient Training/Inference, Meta Learning

Invited Talks

"Lifelong Learning with Dynamically Expandable Networks"

Samsung SDS, Korea, Sep. 2019
Tech. talk, NAVER corp., Korea, July. 2018
Tech. Open Congress(T-T.O.C.), SK-Telecom, Korea, Mar. 2018

"Combined Group and Exclusive Sparsity for Deep Neural Networks"

Korea Software Congress(KSC), Korea, Dec. 2017