Hi, I’m Trenton (he/him)! I am a 3rd year EECS PhD Candidate at the University of Michigan AI lab, where I am a member of MLD3.

I am advised by Jenna Wiens. My primary research area is machine learning fairness and causal inference inspired by healthcare use-cases. My work focuses on:

• Algorithms for mitigating the impact of biases on the performance and fairness of AI models
• Identifying potential sources of inequity in the data used to train AI models

I earned my M.S. in Computer Science from Stanford in 2021, and my B.A. in American Studies from Stanford in 2020. I’ve previously worked on video machine learning robustness with HazyResearch and open-domain conversational AI for the Alexa Grand Prize Socialbot Challenge with the Stanford NLP Group.

I’m always looking to connect with people–please reach out if you want to chat about research!

Email: ctrenton (at) umich (dot) edu

Recent News

• [05/01/2024] My paper, “From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions” was accepted at ICML 2024! We proposed a method for mitigating the impacts of biased missing lables – more info coming soon.

• [03/27/2024] I had the chance to give a lightning talk about my work in bias mitigation in the context of machine learning for healthcare for the NIH Office of Data Science Strategy.

Publications

Chi, Ethan A., Paranjape, Ashwin, See, Abigail, Chiam, Caleb, Chang, Trenton et. al. Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent. SIGDIAL 2022. [paper] [video]

Chang, Trenton, Sjoding, Michael W., and Wiens, Jenna. Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning. MLHC 2022. [paper] [video]

Srivastava, Aarohi, …, Chang, Trenton, …, et. al. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. TMLR 2022. [paper]

Chi, Ethan A., Chiam, Caleb, Chang, Trenton et. al. Neural, Neural Everywhere: Controlled Generation Meets Scaffolded, Structured Dialogue. Alexa Prize Proceedings 2021. [paper]

Preprints/Workshop Papers

Chang, Trenton, and Fu, Daniel Y. Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models. arXiv preprint arXiv:2206.05252. [paper]

Chang, Trenton, Fu, Daniel Y., Li, Sharon, and Ré, Christopher. Beyond the Pixels: Exploring the Effect of Video File Corruptions on Model Robustness. Short Paper, ECCV 2020 Workshop on Adversarial Robustness in the Real World. [paper] [video]

Service

• Reviewed: AISTATS, MLHC, ML4H, KDD (workshop), NeurIPS (workshop). Best Reviewer Award at 2021 Research2Clinics workshop (NeurIPS).
• University Relations Chair, Computer Science & Engineering Graduate Student Organization, University of Michigan (2023-present)
• Panelist, Summer Research Opportunity Program, University of Michigan (2023)
• AI Lab Graduate Admissions Committee Volunteer, Division of Computer Science & Engineering, University of Michigan (2022 & 2024)

Teaching & Mentoring

Undergraduate/graduate level

• [08/2023 - 12/2023] Graduate student instructor, Causality and Machine Learning, EECS 598-009, University of Michigan
• [01/2021 - 03/2021] Research Mentor, Stanford ACM

K-12 level

• [07/2023 - 08/2023] Workshop organizer, Xplore Engineering & Discover Engineering, Division of Computer Science & Engineering, University of Michigan
• [07/2022] Instructor, AI4ALL
• [06/2020 - 08/2020] Instructor, Inspirit AI
• [06/2019 - 08/2019] Residential Counselor/Teaching Assistant for Artificial Intelligence, Stanford Pre-Collegiate Studies