Ke Yu

Joined

June 2019

Names

Ke Yu (Preferred)

Emails

****@pitt.edu (Confirmed)

Personal Links

Google Scholar

ORCID

Career & Education History

PhD student

University of Pittsburgh (pitt.edu)

2018 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Kayhan Batmanghelich

2018 – Present

PhD Advisor

Shyam Visweswaran

2018 – Present

Coauthor

Milos Hauskrecht

2018 – 2020

Expertise

representation learning

Present

machine learning for healthcare

Present

self-supervised learning

Present

graph neural networks

Present

geometric learning

Present

Publications

DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Lung CT Images
Ke Yu, Li Sun, Junxiang Chen, Max Reynolds, Tigmanshu Chaudhary, kayhan Batmanghelich
- OpenReview Archive Direct Upload
- Readers: Everyone
Bridging the Gap: From Post Hoc Explanations to Inherently Interpretable Models for Medical Imaging
Shantanu Ghosh, Ke Yu, Forough Arabshahi, kayhan Batmanghelich
- IMLH 2023 Poster
- Readers: Everyone
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
Nihal Murali, Aahlad Manas Puli, Ke Yu, Rajesh Ranganath, kayhan Batmanghelich
- Accepted by TMLR
- Readers: Everyone
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
Shantanu Ghosh, Ke Yu, Forough Arabshahi, kayhan Batmanghelich
- ICML 2023 Poster
- Readers: Everyone
Route, Interpret, Repeat: Blurring the Line Between Posthoc Explainability and Interpretable Models
Shantanu Ghosh, Ke Yu, Forough Arabshahi, kayhan Batmanghelich
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Shortcut Learning Through the Lens of Early Training Dynamics
Nihal Murali, Aahlad Manas Puli, Ke Yu, Rajesh Ranganath, kayhan Batmanghelich
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Can contrastive learning avoid shortcut solutions?
Joshua David Robinson, Li Sun, Ke Yu, kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone

Ke Yu

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Lung CT Images

Bridging the Gap: From Post Hoc Explanations to Inherently Interpretable Models for Medical Imaging

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

Route, Interpret, Repeat: Blurring the Line Between Posthoc Explainability and Interpretable Models

Shortcut Learning Through the Lens of Early Training Dynamics

Can contrastive learning avoid shortcut solutions?

Co-Authors