Chun-Hao Chang (Kingsley)

Ph.D. Candidate, Computer Science

kingsley _at_

Research Intern
Microsoft Research (MSR) Seattle
Jun. 2019 - Aug 2019
Machine Learning Engineer Intern
Ads Ranking Team, Facebook UK
Jun. 2018 - Aug 2018
University of Toronto
Sep. 2016 - Now

I am studying PhD at Computer Science at University of Toronto with professor Anna Goldenberg. My main research works are in the Interpretability and Robustness with application to Healthcare.


NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
Although Generlized Additive Models (GAMs) are accurate and interpretable, current GAMs do not have differentiability and scalability. In this work we propose a deep learning version of GAM and GA2M that often outperform regular GAMs while remaining interpretable.
TLDR: We develop a deep-learning version of Generalized Additive Model (GAM) and GA2M that is both accurate and interpretable.
Chun-Hao Chang, Rich Caruana, Anna Goldenberg
Submitted to NeurIPS 2021
How Interpretable and Trustworthy are GAMs?
Generalized additive models (GAMs) are useful for data bias discovery and model auditing. But do they always tell the true story of your data, or just its own hallucinated patterns? Also, which GAM algorithm is more accurate and less lying? In this paper we benchmark total 7 different GAMs variants and conclude that tree-based models are more trustworthy. We also design several metrics to decide which GAM is better.
TLDR: We compared total 7 different GAMs and showed which GAM is more trustworthy.
Chun-Hao Chang, Sarah Tan, Ben Lengerich, Anna Goldenberg, Rich Caruana
Accepted in 2021 KDD
Towards Robust Classification Model by Counterfactual and Invariant Data Generation
What makes an image be labeled as a cat? What makes a doctor think there is a tumor in a CT scan? These questions are inherently causal, but typical machine learning (ML) models rely on associations rather than causation. In this paper, we incorporated human causal knowledge into the ML models to make them robust, and show our models still have high accuracy when the environment changes. This is crucial for models to transfer across different environments e.g. different hospital sites in medical applications.
TLDR: We make our models robust to environment shifts by making them depend on the causal features more and spurious features less.
Chun-Hao Chang, George Alexandru Adam, Anna Goldenberg
Accepted in 2021 CVPR
Hidden Risks of Machine Learning Applied to Healthcare: Unintended Feedback Loops Between Models and Future Data Causing Model Degradation
TLDR: We characterize a feedback loop problem that clinicians changing their decisions based on an imperfect ML system that changes the future data distribution.
George Alexandru Adam, Chun-Hao Chang, Anna Goldenberg
Accepted in 2020 Machine Learning for Healthcare (MLHC)
Explaining Image Classifiers by Counterfactual Generation
TLDR: We propose using generative models to ask counterfactual questions to interpret a black-box model (e.g. DNNs).
Chun-Hao Chang, Elliot Creager, Anna Goldenberg, David Duvenaud
Accepted in 2019 ICLR
Dynamic Measurement Scheduling for Adverse Event Forecasting using Deep RL
TLDR: We propose a reinforcement learning approach to help better allocate healthcare resouces for measurement scheduling.
Chun-Hao Chang*, Mingjie Mai*, Anna Goldenberg
Accepted in 2019 ICML

Engineering Experiences

Software Engineer Intern
I interned in the Ads Ranking team of Facebook UK during 2018 summer. My main work is to model counterfactual inference of the ads data to measure lift effects of ads exposure. I investigated various causal approach such as nearest neighbor, causal trees and multi-task learning.
Software Engineer
I interned from 2015 to 2016 in startup company Tripnotice. I built Android app with 500 active daily user, 30,000 downloads and rated as top 5 best travel app in local Taipei newspaper. Besides, I improved hotel recommendation system and constructed hotel booking API with Amadeus.
Android Developer
During my Bachelor, I interned in NTU to develop app for the school course system. I implemented a cross-platform app for student courses information in NTU and obtained 4.3/5 review score and 1,000 downloads in Google Play.