Search Results - "Roh, Yuji"

A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective by Roh, Yuji, Heo, Geon, Whang, Steven Euijong

“…Data collection is a major bottleneck in machine learning and an active research topic in multiple communities. There are largely two reasons data collection…”
Get full text

Data collection and quality challenges in deep learning: a data-centric AI perspective by Whang, Steven Euijong, Roh, Yuji, Song, Hwanjun, Lee, Jae-Gil

“…Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and…”
Get full text

Dependence of sound characteristics on the bowing position in a violin by Roh, YuJi, Kim, Young H.

“…A quantitative analysis of violin sounds produced for different bowing positions over the full length of a violin string has been carried out. An automated…”
Get full text

Comparison of slowness curves of Lamb wave with elastic moduli and crystal structure in silicon wafers by Gyeongwon Yun, Kyung-Min Kim, Yuji Roh, Youngjae Min, Jeong-Ki Lee, Kim, Young H.

“…[100], [110] and [111] single crystal silicon wafers are employed as specimens. Varying incident angle and rotating specimen, leaky Lamb wave (LLW) from…”
Get full text

PFGuard: A Generative Framework with Privacy and Fairness Safeguards by Kim, Soyeon, Roh, Yuji, Heo, Geon, Whang, Steven Euijong

“…Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine…”
Get full text

Improving Fair Training under Correlation Shifts by Roh, Yuji, Lee, Kangwook, Whang, Steven Euijong, Suh, Changho

“…Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training…”
Get full text

Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective by Whang, Steven Euijong, Roh, Yuji, Song, Hwanjun, Lee, Jae-Gil

“…Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and…”
Get full text

Sample Selection for Fair and Robust Training by Roh, Yuji, Lee, Kangwook, Whang, Steven Euijong, Suh, Changho

“…Fairness and robustness are critical elements of Trustworthy AI that need to be addressed together. Fairness is about learning an unbiased model while…”
Get full text

Responsible AI Challenges in End-to-end Machine Learning by Whang, Steven Euijong, Tae, Ki Hyun, Roh, Yuji, Heo, Geon

“…Responsible AI is becoming critical as AI is widely used in our everyday lives. Many companies that deploy AI publicly state that when training a model, we not…”
Get full text

FairBatch: Batch Selection for Model Fairness by Roh, Yuji, Lee, Kangwook, Whang, Steven Euijong, Suh, Changho

“…Training a fair machine learning model is essential to prevent demographic disparity. Existing techniques for improving model fairness require broad changes in…”
Get full text

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views by Roh, Yuji, Liu, Qingyun, Gui, Huan, Yuan, Zhe, Tang, Yujin, Whang, Steven Euijong, Liu, Liang, Bi, Shuchao, Hong, Lichan, Chi, Ed H, Zhao, Zhe

“…Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of…”
Get full text

A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective by Roh, Yuji, Heo, Geon, Whang, Steven Euijong

“…Data collection is a major bottleneck in machine learning and an active research topic in multiple communities. There are largely two reasons data collection…”
Get full text

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training by Roh, Yuji, Lee, Kangwook, Whang, Steven Euijong, Suh, Changho

“…Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training…”
Get full text

Inspector Gadget: A Data Programming-based Labeling System for Industrial Images by Heo, Geon, Roh, Yuji, Hwang, Seonghyeon, Lee, Dayun, Whang, Steven Euijong

“…Proceedings of the VLDB Endowment, Volume 14, Issue 1, September 2020 As machine learning for images becomes democratized in the Software 2.0 era, one of the…”
Get full text

Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach by Tae, Ki Hyun, Roh, Yuji, Oh, Young Hun, Kim, Hyunsu, Whang, Steven Euijong

“…The wide use of machine learning is fundamentally changing the software development paradigm (a.k.a. Software 2.0) where data becomes a first-class citizen, on…”
Get full text