Ju Min Lee

Ju Min Lee

Auto-generated profile, based on publicly available information

Ju Min Lee

Yonsei University, Republic of Korea

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
15 July 2014 in Transplantation
Verified
Journal Article
Open access
JLJ. Lee
J. Lee
DJDong Jin Joo
Dong Jin Joo
ALA. Lee
A. Lee
SLS. Lee
S. Lee
DHDai Hoon Han
Dai Hoon Han
MKMyung-Joon Kim
Myung-Joon Kim

9 January 2026 in Journal of Systems Architecture
Verified
Journal Article
Closed access
JLJaeho Lee
Jaeho Lee
JLJu Min Lee
Ju Min Lee
HJHaeeun Jeong
Haeeun Jeong
HKHyunho Kwon
Hyunho Kwon
YKYoungsok Kim
Youngsok Kim
HKHanjun Kim
Hanjun Kim

12 August 2024
Verified
Conference Paper
Open access
SSSeungbin Song
Seungbin Song
JLJu Min Lee
Ju Min Lee
HJHaeeun Jeong
Haeeun Jeong
HKHyunho Kwon
Hyunho Kwon
SJShinnung Jeong
Shinnung Jeong
HKHanjun Kim
Hanjun Kim
Since the increasing complexity of deep learning models, tensor decomposition is one of the promising solutions that reduce computational complexity in deep learning models. By decomposing a convolution layer with a large weight tensor into multiple layers with smaller weight tensors, tensor decomposition can reduce the number of operations and weight memory spaces. However, existing tensor decomposition schemes face difficulties in reducing peak memory usage of the entire inference. The decomposed layers produce the reduced-sized tensors during inference, but the reduced tensors should be restored to their original sizes due to skip connections and non-decomposed activation layers between the decomposed layers. To reduce the peak memory usage of the end-to-end inference of the decomposed models, this work proposes a new tensor memory optimization scheme and its prototype compiler, called TeMCO. TeMCO replaces the original internal tensors used in the skip connections with reduced internal tensors derived by the decomposed layers. In addition, TeMCO fuses the decomposed layers and the non-decomposed activation layer and thus keeps the reduced internal tensors produced without restoring them. Thanks to the optimizations, this work reduces memory usage of internal tensors by 75.7% for 10 models of 5 deep learning architectures.