no code implementations • 22 Nov 2023 • Lingjiao Chen, Bilge Acun, Newsha Ardalani, Yifan Sun, Feiyang Kang, Hanrui Lyu, Yongchan Kwon, Ruoxi Jia, Carole-Jean Wu, Matei Zaharia, James Zou
As Machine Learning (ML) systems continue to grow, the demand for relevant and comprehensive datasets becomes imperative.
1 code implementation • 2 Oct 2023 • Yongchan Kwon, Eric Wu, Kevin Wu, James Zou
Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline.
1 code implementation • 4 May 2023 • Weixin Liang, Yining Mao, Yongchan Kwon, Xinyu Yang, James Zou
Our work highlights the importance of understanding the nonlinear effects of model improvement on performance in different subpopulations, and has the potential to inform the development of more equitable and responsible machine learning models.
2 code implementations • 16 Apr 2023 • Yongchan Kwon, James Zou
As a result, it has been recognized as infeasible to apply to large datasets.
1 code implementation • 27 Sep 2022 • Yongchan Kwon, James Zou
On several real-world datasets, we demonstrate that the influential features identified by WeightedSHAP are better able to recapitulate the model's predictions compared to the features identified by the Shapley value.
2 code implementations • 3 Mar 2022 • Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, James Zou
Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization.
no code implementations • 26 Jan 2022 • Yongchan Kwon, Antonio Ginart, James Zou
We introduce a new environment that allows ML predictors to use active learning algorithms to purchase labeled data within their budgets while competing against each other to attract users.
2 code implementations • 26 Oct 2021 • Yongchan Kwon, James Zou
Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning.
no code implementations • 15 Sep 2020 • Antonio Ginart, Eva Zhang, Yongchan Kwon, James Zou
A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e. g. in the form of a Yelp review).
no code implementations • 2 Jul 2020 • Yongchan Kwon, Manuel A. Rivas, James Zou
Distributional data Shapley value (DShapley) has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning.
1 code implementation • ICML 2020 • Yongchan Kwon, Wonyoung Kim, Joong-Ho Won, Myunghee Cho Paik
We show that our approximation and risk consistency results naturally extend to the cases when data are locally perturbed.
no code implementations • 20 Mar 2019 • Seongok Ryu, Yongchan Kwon, Woo Youn Kim
Deep neural networks have outperformed existing machine learning models in various molecular applications.
1 code implementation • 28 Jan 2019 • Yongchan Kwon, Wonyoung Kim, Masashi Sugiyama, Myunghee Cho Paik
We consider the problem of learning a binary classifier from only positive and unlabeled observations (called PU learning).
no code implementations • 19 Nov 2018 • Seongok Ryu, Yongchan Kwon, Woo Youn Kim
In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions.
no code implementations • MIDL 2018 Conference 2018 • Yongchan Kwon, Joong-Ho Won, Beom Joon Kim, Myunghee Cho Paik
Most recent research of neural networks in the field of computer vision has focused on improving accuracy of point predictions by developing various network architectures or learning algorithms.
General Classification Ischemic Stroke Lesion Segmentation +2