Dr. Yao Quanming is an Assistant Professor and Doctoral Advisor in the Department of Electronic Engineering at Tsinghua University. He is a recipient of the National High-Level Young Talents Program. He obtained his Ph.D. from the Department of Computer Science at the Hong Kong University of Science and Technology, and subsequently served as Chief Researcher at 4Paradigm, where he founded and led the machine learning research team. His primary research focuses on methodologies and principles of machine learning, particularly their applications in scientific intelligence and the theoretical foundations of large-scale models.

He has published over 100 top-tier papers in venues including Nature Computational Science, Nature - Communications, JMLR, IEEE TPAMI, ICML, NeurIPS, and ICLR, accumulating over 12,000 citations. His noise-resistant - label algorithm "Co-teaching" is a milestone in robust learning; his survey on few-shot learning is the ‌most-cited paper in ACM Computing Surveys in the last half-decade‌; his automated graph learning series (e.g., TPAMI 2023) has ‌consistently ranked #1 on the Open Graph Benchmark leaderboard‌; and his work on novel drug-drug interactions using pharmaceutical networks was published in a Nature sub-journal.

He serves as an ‌Area Chair‌ for leading machine learning conferences (ICML, NeurIPS, ICLR) and as ‌Senior Editor‌ for the flagship journal Neural Networks, and ‌Editor‌ for Machine Learning and Transactions on Machine Learning Research. He has received numerous prestigious awards, including:

- MIT Technology Review's "35 Innovators Under 35" (Global AI List)

- Ant Intech Technology Award (inaugural)

- INNS Early Career Award

- Hong Kong Young Scientist Award (HKSTS)

- Wu Wen Jun AI Excellent Youth Award

- Google PhD Fellowship

- Ranked among Top 25 Global Chinese AI Young Scholars (ML)

- Forbes 30 Under 30 China

- World's Top 2% Most-Cited Scientists (Elsevier-Stanford)

- Invited to present an Early Career Spotlight talk at AAAI 2024

At Tsinghua, he teaches the core undergraduate course "Data and Algorithms" and contributes to graduate courses "Advanced Machine Learning" and "High-Tech Talent and Enterprise Development." He serves as Head Teacher for the "AI + Systems" aptitude-based instruction track in the Department of Electronic Engineering. ‌Since joining Tsinghua, students under his supervision have received the Tsinghua University Outstanding Undergraduate Thesis Award for three consecutive years.‌ Projects he advised in the Undergraduate Research Training Program (SRT) won the ‌University-level Grand Prize (1 of 5)‌ and the ‌Challenge Cup Grand Prize (sole recipient in the Information Track)‌.

‌Representative Publications‌ (* indicates corresponding author; _ indicates co-first authorship)

[1].    Quanming Yao, Zhenqian Shen, Yaqing Wang*, Dejing Dou. Property-Aware Relation Networks for Few-Shot Molecular Property Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2024

[2].    Yongqi Zhang, Quanming Yao*, Ling Yue, Xian Wu, Ziheng Zhang, Zhenxi Lin, Yefeng Zheng. Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Network. Nature Computational Science. 2023.

[3].    Yongqi Zhang, Quanming Yao*, James T. Kwok. Bilinear Scoring Function Search for Knowledge Graph Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2023.

[4].    Quanming Yao, Yaqing Wang, Bo Han, James T. Kwok. Efficient Low-rank Tensor Learning with Nonconvex Regularization. Journal of Machine Learning Research (JMLR). 2022.

[5].    Yaqing Wang, Quanming Yao*, James T. Kwok, Lionel Ni. Generalizing from a Few Examples: A Survey on Few-Shot Learning. ACM computing surveys (CSUR). 2020. 

[6].    Quanming Yao*, James T. Kwok, Taifeng Wang, and Tie-Yan Liu. Large-scale low-rank matrix learning with nonconvex regularizers. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2019

[7].    Quanming Yao* and James T. Kwok. Efficient learning with nonconvex regularizers by nonconvexity redistribution. Journal of Machine Learning Research (JMLR). 2018.

[8].    Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama. Co-teaching: Robust training deep neural networks with extremely noisy labels. Advances in Neural Information Processing Systems (NeurIPS). 2018.