Haonan Duan
I am a PhD candidate in computer science at the University of Toronto, supervised by Prof. Chris Maddison and Prof. Nicolas Papernot. I am interested in broad areas of machine learning. My current research focuses on AI for science and trustworthy ML. Beforehand, I completed my MMath and BMath in computer science at the University of Waterloo, supervised by Prof. Pascal Poupart.
Workshop & Preprints
-
PAIR: Boosting the Predictive Power of Protein Representations with a Corpus of Text Annotations
Haonan Duan*, Marta Skreta*, Leonardo Cotta, Ella Miray Rajaonson, Nikita Dhawan, Alan Aspuru-Guzik, Chris J. Maddison
ICML 2024 AI for Science Workshop
[paper]
-
Meta-Designing Quantum Experiments with Language Models
Soeren Arlt, Haonan Duan, Felix Li, Sang Michael Xie, Yuhuai Wu, Mario Krenn
ICML 2024 AI for Science Workshop
[paper]
-
On the privacy risk of in-context learning
Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot, Franziska Boenisch
ACL 2023 Trustworthy NLP Workshop
[paper]
Papers
-
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan*, Adam Dziedzic*, Nicolas Papernot, Franziska Boenisch
Conference on Neural Information Processing Systems (NeurIPS), 2023.
[paper]
-
Dataset Inference for Self-Supervised Models
Adam Dziedzic*, Haonan Duan*, Muhammad Ahmad Kaleem*, Nikita Dhawan, Jonas Guan, Yannis Cattan, Franziska Boenisch, Nicolas Papernot
Conference on Neural Information Processing Systems (NeurIPS), 2022.
[paper]
-
Augment with Care: Contrastive Learning for Combinatorial Problems
Haonan Duan*, Pashootan Vaezipoor*, Max B. Paulus, Yangjun Ruan, Chris J. Maddison
International Conference on Machine Learning (ICML), 2022.
[paper]
-
Distributional Reinforcement Learning with Monotonic Splines
Yudong Luo, Guiliang Liu, Haonan Duan, Oliver Schulte, Pascal Poupart
International Conference on Learning Representations (ICLR), 2022
[paper]
-
Online Bayesian Moment Matching based SAT Solver Heuristics
Haonan Duan*, Saeed Nejati*, George Trimponias, Pascal Poupart and Vijay Ganesh
International Conference on Machine Learning (ICML), 2020.
[paper]
-
Discriminative Training of Feed-Forward and Recurrent Sum-Product Networks by Extended Baum-Welch
Haonan Duan, Abdullah Rashwan, Pascal Poupart and Zhitang Chen
International Journal of Approximate Reasoning (IJAR), Volume 124, September 2020, Pages 66-81
[paper][link]
* below indicates equal contribution
Service
-
Conference reviewer: ICLR (2020-2023), ICML(2021-2023), NeurIPS(2021-2023), AISTATS(2022)
Industry Experience
-
Software Engineer Intern @
Uber
Jan. 2021 - Apr. 2021
-
Data Scientist Intern @
Thomson Reuters
May. 2020 - Aug. 2021
Selected Honors & Awards
I am grateful for the organizations and people below to support my study and research: