Yongqiang Chen @ CLeaR

I am an postdoctoral researcher at CMU-CLeaR group with Prof. Kun Zhang. Previously, I defended my Ph.D. in CSE at CUHK in 2024, working with Prof. James Cheng, and Prof. Bo Han at TMLR group. During my research journey, I also had wonderful time at RIKEN AIP, Tencent AI Lab, and Microsoft Research Asia.

My research focuses on developing new foundations of machine learning with causality, that promotes multiple desirable properties such as alignment, generalization, and interpretability of modern machine learning systems, empowering industrial applications and scientific practice with AI.

My PhD thesis made some early attempts on this problem. Meanwhile, I am always open for collaborations and communications. Our teams are also recruiting Research Assistants, Mphil and PhD students. The positions are available at multiple institutes. If you are interested in working with me, please feel free to drop me an email.

Selected Preprints and Publications

Email me if you have any questions about my papers or code. * indicates equal contributions.

Discovery of the Hidden World with Large Language Models

Chenxi Liu*, Yongqiang Chen*, Tongliang Liu, Mingming Gong, James Cheng, Bo Han, and Kun Zhang

Advances in Neural Information Processing Systems (NeurIPS), 2024.

[paper]

[project page]

Do CLIPs Always Generalize Better than ImageNet Models?
Qizhou Wang*, Yong Lin*, Yongqiang Chen*, Ludwig Schmidt, Bo Han, Tong Zhang
In Advances in Neural Information Processing Systems (NeurIPS), 2024.
[paper] [project page]
HIGHT: Hierarchical Graph Tokenization for Graph-Language Alignment
Yongqiang Chen, Quanming Yao, Juzheng Zhang, James Cheng, and Yatao Bian
In ICML 2024 Workshop on Foundation Models in the Wild, 2024.
[paper] [project page]
How Interpretable are Interpretable Graph Neural Networks?
Yongqiang Chen, Yatao Bian, Bo Han, James Cheng
In International Conference on Machine Learning (ICML), 2024.
Also appeared In ICLR MLGenX workshop, 2024. Spotlight presentation.
[paper] [code]
Enhancing Evolving Domain Generalization through Dynamic Latent Representations
Binghui Xie, Yongqiang Chen, Jiaqi Wang, Kaiwen Zhou, Bo Han, Wei Meng, James Cheng
In Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024. Oral presentation (2.2%).
[paper] [code]
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Yongqiang Chen*, Wei Huang*, Kaiwen Zhou*, Yatao Bian, Bo Han, James Cheng
In Advances in Neural Information Processing Systems (NeurIPS), 2023.
Also presented in ICLR Workshop on Domain Generalization (ICLR DG) Spotlight presentation.
[paper] [code] [slides]
Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Yongqiang Chen, Yatao Bian, Kaiwen Zhou, Binghui Xie, Bo Han, James Cheng
In Advances in Neural Information Processing Systems (NeurIPS), 2023.
Also presented in ICLR Workshop on Domain Generalization (ICLR DG) Spotlight presentation.
[paper] [code] [slides]
Towards Out-of-Distribution Generalizable Predictions of Chemical Kinetics Properties
Zihao Wang*, Yongqiang Chen*, Yang Duan, Weijiang Li, Bo Han, James Cheng, Hanghang Tong
In NeurIPS Workshop on AI for Science Oral presentation, 2023.
[paper] [code]
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in OOD Generalization
Yongqiang Chen, Kaiwen Zhou, Yatao Bian, Binghui Xie, Bingzhe Wu, Peilin Zhao, Bo Han, James Cheng and others.
In International Conference on Learning Representations (ICLR), 2023. Oral presentation at ICLR DG.
Presented at ICML PODS, 2022, with Kaiwen Zhou*.
[paper] [code] [talk] [slides] [Wilds Leaderborad] [zh-cn blog]
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Yongqiang Chen, Yonggang Zhang, Yatao Bian, Han Yang, Kaili Ma, Binghui Xie, Tongliang Liu, Bo Han, James Cheng
In Advances in Neural Information Processing Systems (NeurIPS), 2022. Spotlight presentation (5.2%).
Presented at ICML SCIS 2022. 🔥SOTA results in GOOD Benchmark🔥.
[paper] [workshop ver.] [code] [talk] [slides] [zh-cn blog]
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Yongqiang Chen, Han Yang, Yonggang Zhang, Kaili Ma, Tongliang Liu, Bo Han, James Cheng
In International Conference on Learning Representations (ICLR), 2022.
[paper] [code] [talk] [slides]

Yongqiang Chen

Selected Preprints and Publications

Selected Awards

Academic Service