Young Eun Kim

Young Eun Kim

Auto-generated profile, based on publicly available information

Young Eun Kim

Carbon Conversion Research Laboratory, Korea Institute of Energy Research, 152 Gajeong-ro, Yuseong-gu, Daejeon 34129, Republic of Korea

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 May 2018 in Angewandte Chemie International Edition
Verified
Journal Article
Closed access
PDF file
Wonhee LeeWonhee Lee
Wonhee Lee
YKYoung Eun Kim
Young Eun Kim
MYMin Hye Youn
Min Hye Youn
SJSoon Kwan Jeong
Soon Kwan Jeong
KPKi Tae Park
Ki Tae Park

11 July 2023 in ACS Energy Letters
Verified
Journal Article
Closed access
YKYoung Eun Kim
Young Eun Kim
YKYou Na Ko
You Na Ko
BAByeong-Seon An
Byeong-Seon An
JHJumi Hong
Jumi Hong
YJYe Eun Jeon
Ye Eun Jeon
Wonhee LeeWonhee Lee
Wonhee Lee

1 October 2019 in Journal of Industrial and Engineering Chemistry
Verified
Journal Article
Closed access
YKYoung Eun Kim
Young Eun Kim
Wonhee LeeWonhee Lee
Wonhee Lee
MYMin Hye Youn
Min Hye Youn
SJSoon Kwan Jeong
Soon Kwan Jeong
HKHak Joo Kim
Hak Joo Kim
KPKi Tae Park
Ki Tae Park

8 May 2018 in Angewandte Chemie
Verified
Journal Article
Closed access
PDF file
Wonhee LeeWonhee Lee
Wonhee Lee
YKYoung Eun Kim
Young Eun Kim
MYMin Hye Youn
Min Hye Youn
SJSoon Kwan Jeong
Soon Kwan Jeong
KPKi Tae Park
Ki Tae Park

11 October 2024 in Materials Today Energy
Verified
Journal Article
Closed access
YJYe Eun Jeon
Ye Eun Jeon
JHJumi Hong
Jumi Hong
BAByeong-Seon An
Byeong-Seon An
HKHyun You Kim
Hyun You Kim
CKChunjoong Kim
Chunjoong Kim
YKYoung Eun Kim
Young Eun Kim

1 October 2020
Verified
Conference Paper
Closed access
HPHyoungseob Park
Hyoungseob Park
MJMinki Jeong
Minki Jeong
YKYoungeun Kim
Youngeun Kim
CKChangick Kim
Changick Kim
Filtering noisy labels is crucial for robust training of deep neural networks. To train networks with noisy labels, sampling methods have been introduced, which sample the reliable instances to update networks using only sampled data. Since they rarely employ the non-sampled data for training, these methods have a fundamental limitation that they reduce the amount of the training data. To alleviate this problem, our approach aims to fully utilize the whole dataset by leveraging the information of the sampled data. To this end, we propose a novel graph-based learning framework that enables networks to propagate the label information of the sampled data to adjacent data, whether they are sampled or not. Also, we propose a novel self-training strategy to utilize the non-sampled data without labels and to regularize the network update using the information of the sampled data. Our method outperforms state-of-the-art sampling methods.