北京雁栖湖应用数学研究院

韩立岩 , 李振 , 龙飞 , 汤珂 , 王玉

王雅晴

2025年03月21日 15:00 至 16:30

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.

王雅晴博士现任北京雁栖湖应用数学研究院（BIMSA）副研究员。她于 2019 年获得香港科技大学计算机科学与工程博士学位，导师为 Lionel M. Ni 教授和 James T. Kwok 教授。2019 年至 2024 年，她通过 AIDU 计划加入百度研究院，担任资深研究员。王博士已在 ICML、NeurIPS、ICLR、KDD、TheWebConf、SIGIR、AAAI、IJCAI、EMNLP、TPAMI、JMLR、CSUR 和 TIP 等国际顶级会议和期刊上发表论文 40 篇，论文引用超过 6000 次。她曾获得香港政府博士奖学金（2014–2018），入选北京市科技新星计划（2025）、AAAI New Faculty Highlight（2026）和 IJCAI Early Career Spotlights（2026），并入选全球前 2% 顶尖科学家榜单（2024–2025）。她是 ACM、IEEE 和 CCF 高级会员。王博士担任Neural Networks执行编委、Machine Learning编委以及ACL Rolling Review 领域主席。她的相关技术已在百度、美团等企业的大规模真实业务系统中部署应用。
王博士的研究方向包括机器学习、人工智能与数据科学。她致力于发展数据高效的机器学习方法，从而高效、低成本的解决真实世界中的实际问题。目前，她的主要研究兴趣包括：
- 少样本学习、元学习与上下文学习
- 数据高效的大模型智能体学习
- 冷启动推荐与个性化用户建模
- 面向科学与数学的人工智能（AI for Science and Mathematics / AI + X）