Kehang Han

Kehang Han

I joined Google Brain as an AI Resident in 2020 and now am a Research Engineer there. My research focus has been Graph Neural Networks and Bayesian methods to make deep learning models more reliable (e.g., reduce overconfidence, improve calibration) under distributional shift. Before that I was a senior data scientist at Staples working on Operations Research and Internet of Things. I obtained PhD from MIT on Chemical Engineering and Computation.

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Plex: Towards Reliability using Pretrained Large Model Extensions
Dustin Tran
Jeremiah Liu
Michael W. Dusenberry
Du Phan
Mark Patrick Collier
Jie Jessie Ren
Kehang Han
Zi Wang
Zelda Mariet
Clara Huiyi Hu
Neil Band
Tim G. J. Rudner
Karan Singhal
Zachary Nado
Joost van Amersfoort
Andreas Christian Kirsch
Rodolphe Jenatton
Nithum Thain
Honglin Yuan
Kelly Buchanan
Kevin Patrick Murphy
D. Sculley
Yarin Gal
Zoubin Ghahramani
Jasper Roland Snoek
Balaji Lakshminarayanan
ICML 2022 Pre-training Workshop (2022)
Improving Hit-finding: Multilabel Neural Architecture with DEL
Jin Xu
Kehang Han
Steven Kearnes
AI for Science NeurIPS 2021 workshop (2021)
Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
Kehang Han
Balaji Lakshminarayanan
Jeremiah Liu
DistShift NeurIPS 2021 workshop (2021) (to appear)
Search on Google Scholar