Ke Yu

     

Contact:

yu.ke@pitt.edu

About Me

I am a Research Engineer at Google, working on generative AI for 3D.

I got my Ph.D. from Intelligent Systems at the University of Pittsburgh, advised by Prof. Kayhan Batmanghelich. My doctoral research focused on developing sample-efficient representation learning methods, particularly for medical applications.

Before that, I received M.S. in statistics from Georgia Institute of Technology and had seven years of experience in industry.

Education

University of Pittsburgh, USA
Ph.D. in Intelligent Systems

Georgia Institute of Technology, USA
M.S. in Statistics

Huazhong University of Science and Technology, China
B.S. in Electrical and Electronics Engineering
B.S. in Computer Science

Publications

* indicates equal contribution

Anatomy-guided weakly-supervised abnormality localization in chest x-rays
Ke Yu, Shantanu Ghosh, Zhexiong Liu, Christopher Deible, Kayhan Batmanghelich
MICCAI 2022 / Paper / Code
Boosting the interpretability of clinical risk scores with intervention predictions
Eric Loreaux*, Ke Yu*, Jonas Kemp, Martin Seneviratne, Christina Chen, Subhrajit Roy, Ivan Protsyuk, Natalie Harris, Alexander D’Amour, Steve Yadlowsky, Ming-Jun Chen
KDD 2022, DSHealth Workshop / Paper /
Hierarchical amortized GAN for 3D high resolution medical image synthesis
Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich
IEEE Journal of Biomedical and Health Informatics / Paper / Code
De novo prediction of cell-drug sensitivities using deep learning-based graph regularized matrix factorization
Shuangxia Ren*, Yifeng Tao*, Ke Yu, Yifan Xue, Russell Schwartz, Xinghua Lu
PSB 2022 / Paper /
Extracting disease-relevant features with adversarial regularization
Junxiang Chen, Li Sun, Ke Yu, Kayhan Batmanghelich
BIBM 2021 / Paper /
Can contrastive learning avoid shortcut solutions?
Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra
NeurIPS 2021 / Paper / Code
Conext Matters: Graph-based Self-supervised Represenation Learning for Medical Images
Li Sun*, Ke Yu*, Kayhan Batmanghelich
AAAI 2021 / Paper / Code
Semi-supervised Hierarchical Drug Embedding in Hyperbolic Space
Ke Yu, Shyam Visweswaran, Kayhan Batmanghelich
Journal of Chemical Information and Modeling / Paper / Code
Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
Ke Yu*, Li Sun*, Kayhan Batmanghelich
NeruIPS 2020, Medical Imaging Workshop / Paper
Hyperbolic Molecular Representation Learning for Drug Repositioning
Ke Yu, Shyam Visweswaran, Kayhan Batmanghelich
NeruIPS 2020, ML4Molecules Workshop / Paper
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich
NeruIPS 2020, Medical Imaging Workshop / Paper
Monitoring ICU mortality risk with a long short-term memory recurrent neural network
Ke Yu*, Mingda Zhang, Tianyi Cui, Milos Hauskrecht,
PSB 2020 / Paper / Code
Monitoring ICU mortality risk with a long short-term memory recurrent neural network
Ke Yu*, Mingda Zhang, Tianyi Cui, Milos Hauskrecht,
PSB 2020 / Paper / Code