Beijing Institute of Mathematical Sciences and Applications

Liyan Han , Zhen Li , Fei Long , Ke Tang , Yu Wang

Yaqing Wang

Friday, March 21, 2025 3:00 PM - 4:30 PM

A3-2a-302

Zoom 637 734 0280 (BIMSA)

In the current field of AI-assisted scientific research (AI for Science), particularly in drug discovery and biomedicine, we often face the challenge of scarce labeled data. Few-shot learning has become a key technology to address this challenge, as it can effectively leverage limited data for learning and prediction. In this report, I will introduce a series of machine learning algorithms developed specifically to improve data efficiency and prediction accuracy in AI for Science under data scarcity. I will discuss the application of few-shot learning techniques in molecular property prediction, reviewing existing technologies and presenting our proposed Property-Aware Relationship Network (PAR) (NeurIPS 2021, TPAMI 2024) and parameter-efficient Graph Neural Network Adapter (PACIA) (IJCAI 2024). PAR optimizes the relationship representations between molecules by introducing a property-aware molecular encoder and a dependency-query-based relational graph learning module, thereby improving prediction accuracy for various chemical properties. Meanwhile, PACIA enhances few-shot molecular property prediction performance by generating a small number of adaptive parameters to modulate the information propagation process in graph neural networks. In addition, I will introduce the KnowDDI technique (Communications Medicine 2024), which enhances drug representations by leveraging large biomedical knowledge graphs and explains predicted drug-drug interactions (DDIs) by learning knowledge subgraphs of drug pairs, effectively addressing the issue of scarce known data. KnowDDI not only improves prediction performance but also enhances the interpretability of the model, making the prediction process more transparent and trustworthy. Finally, I will share the vision of applying few-shot learning techniques in broader scientific research.

Dr. Yaqing Wang is currently an Associate Professor at the Beijing Institute of Mathematical Sciences and Applications (BIMSA). She received her Ph.D. in Computer Science and Engineering from the Hong Kong University of Science and Technology in 2019, under the supervision of Professor Lionel M. Ni and Prof. James T. Kwok. From 2019 to 2024, she was a Staff Researcher at Baidu Research, recruited through the AIDU Program. Dr. Wang has published 40 papers in top-tier international conferences and journals, including ICML, NeurIPS, ICLR, KDD, TheWebConf, SIGIR, AAAI, IJCAI, EMNLP, TPAMI, JMLR, CSUR, and TIP, with more than 6000 citations. She is a recipient of the Hong Kong PhD Fellowship (2014–2018), was selected for Beijing Nova Program (2025), AAAI New Faculty Highlight (2026), IJCAI Early Career Spotlights (2026), and has been listed among the World’s Top 2% Scientists (2024-2025). She is a senior member of ACM, IEEE, and CCF. Dr. Wang serves as an Associate Editor of Neural Networks, editorial board member of Machine Learning and Area Chair for ACL Rolling Review. Her techniques have been deployed in large-scale real-world systems at Baidu, Meituan, and other industry applications.
Dr. Yaqing Wang’s research focuses on machine learning, artificial intelligence, and data science. She strives to develop refined, data-efficient, and cost-effective scientific solutions to real-world problems. Her current research interests include:
- Few-Shot Learning, Meta-Learning, and In-Context Learning
- Data-Efficient Agentic Learning
- Cold-Start Recommendation and Personalized User Modeling
- AI for Science and Mathematics (AI + X)