BIMSA > 王雅晴
副研究员 王雅晴

团队: 人工智能和机器学习

办公室: A13-105

邮箱: wangyaqing@bimsa.cn

研究方向: 机器学习，数据挖掘，智能科学

个人主页: https://wangyaqing.github.io/

个人简介

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）

研究兴趣

  • 小样本学习和元学习
  • 图学习
  • 生物智能、数学智能
  • 大模型和智能体
  • 冷启动推荐和用户建模

教育经历

  • 2014 - 2019      香港科技大学      计算机科学及工程学系      哲学博士      (Supervisor: 倪明选教授，郭天佑教授)
  • 2010 - 2014      山东大学      计算机科学与技术      工学学士

工作经历

  • 2024 -      北京雁栖湖应用数学研究院      副研究员
  • 2019 - 2024      百度研究院      资深研究员

出版物

  • [1] ZH Wong, H Yang, Q Yao, Y Wang, Robust Heterogeneous Network Representation Learning by Multifaceted Curriculum Training, Neural Networks (NN), 196, 108438 (2026)
  • [2] Z Zhang, Q Yao, Y Wang, LLM-Empowered Representation Learning for EmergingItem Recommendation, Data Analyticsand Topology (DAT), 2 (2026)
  • [3] S Wu, Y Wang, Q Yao, Searching to Modulate for Cold-Start Recommendation, accepted by IEEE TransactionsonPattern Analysis andMachine Intelligence (TPAMI) (2026)
  • [4] Y Tan, Q Yao, Y Wang, DGNet: Learning Spatiotemporal PDEs with Discrete Green Networks, accepted by International Conference on Learning Representations (ICLR) (2026)
  • [5] Y Wang, From Few-Shot Learning to Data-Efficient Intelligence, AAAI Conference on Artificial Intelligence (AAAI) (2025)
  • [6] Jiale Fu, Yaqing Wang, Simeng Han, Jiaming Fan, Xu Yang, GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning, AAAI Conference on Artificial Intelligence (AAAI) (2025)
  • [7] H Nie, Y Wang, M Zhou, F Pan, Q Yao, Z Wang, AdaPA-Agent: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling, Advances in Neural Information Processing Systems (NeurIPS) (2025)
  • [8] S Wu, Y Wang, Q Yao, Learning to Learn with Contrastive Meta-Objective, Advances in Neural Information Processing Systems (NeurIPS) (2025)
  • [9] Haihua XIE, Yinzhu CHENG, Yaqing WANG, Miao HE, Mingming SUN, RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrations, The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) (2025)
  • [10] Haotong Du, Yaqing Wang, Fei Xiong, Lei Shao, Ming Liu, Hao Gu, Quanming Yao, Zhen Wang, PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2025)
  • [11] Shiguang Wu, Yaqing Wang, Quanming Yao, Why In-Context Learning Models are Good Few-Shot Learners?, International Conference on Learning Representations (ICLR) (2025)
  • [12] Quanming Yao, Yongqi Zhang, Yaqing Wang, Nan Yin, James Kwok, Qiang Yang, Beyond Scaleup: Knowledge‐Aware Parsimony Learning from Deep Networks, AI Magazine, 46(1), e12211 (2025)
  • [13] Yaqing Wang, Hongming Piao, Daxiang Dong, Quanming Yao, and Jingbo Zhou, Warming Up Cold-Start CTR Prediction by Learning Item-Specific Feature Interactions, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (2024)
  • [14] Shiguang Wu, Yaqing Wang, and Quanming Yao, PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction, International Joint Conference on Artificial Intelligence (IJCAI) (2024)
  • [15] Yongpan Zou,Yunshu Wang, Haozhi Dong, Yaqing Wang, Yanbo He, and Kaishun Wu, PreGesNet: Few-Shot Acoustic Gesture Recognition Based on Task-Adaptive Pretrained Networks, IEEE Transactions on Mobile Computing (2024)
  • [16] Daxiang Dong, Shiguang Wu, Yaqing Wang, Jingbo Zhou, Haifeng Wang, ColdU: Cold-start Recommendation with User-specific Modulation, IEEE Conference on Artificial Intelligence (CAI) (2024)
  • [17] Yaqing Wang, Zaifei Yang, and Quanming Yao, Accurate and Interpretable Drug-drug Interaction Prediction Enabled by Knowledge Subgraph Learning, Communications Medicine (Commun. Med.,Nature Portfolio), 4(1), 59 (2024)
  • [18] Quanming Yao, Zhenqian Shen, Yaqing Wang†, and Dejing Dou, Property-Aware Relation Networks for Few-Shot Molecular Property Prediction, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 46(8), 5413-5429 (2024)
  • [19] Yan Wen, Chen Gao, Lingling Yi, Liwei Qiu, Yaqing Wang, and Yong Li, Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering, ACMSIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (2023)
  • [20] Jiang Bian, Jizhou Huang, Shilei Ji, Yuan Liao, Xuhong Li, Qingzhong Wang, Jingbo Zhou, Yaqing Wang, Dejing Dou, and Haoyi Xiong, Feynman: Federated Learning-based Advertising for Ecosystems-Oriented Mobile Apps Recommendation, IEEE Transactions on Services Computing (TSC) (2023)
  • [21] Zhen Wang, Hongyi Nie, Wei Zheng, Yaqing Wang, and Xuelong Li, A Novel Tensor Learning Model for Joint Relational Triplet Extraction, IEEE Transactions on Cybernetics (TCYB), 54(4), 2483-2494 (2023)
  • [22] Shiguang Wu, Yaqing Wang, Qinghe Jing, Daxiang Dong, Dejing Dou, and Quanming Yao, ColdNAS: Search to Modulate for User Cold-Start Recommendation, The Web Conference (TheWebConf/WWW) (2023)
  • [23] Xuhong Li, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, and Dejing Dou, Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models, Machine Learning (MLJ), 112(6), 2193-2209 (2023)
  • [24] Yan Li, Xinjiang Lu, Yaqing Wang, and Dejing Dou, Generative time series forecasting with diffusion, denoise, and disentanglement, Advances in Neural Information Processing Systems (NeurIPS), 35, 23009-23022 (2022)
  • [25] Kexin Zheng, Yaqing Wang, Quanming Yao, and Dejing Dou, Simplified Graph Learning for Inductive Short Text Classification, Conference on Empirical Methods in Natural Language Processing (EMNLP) (2022)
  • [26] Quanming Yao, Yaqing Wang, Bo Han, and James T. Kwok, Efficient Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization, Journal of Machine Learning Research (JMLR), 23(136), 1-60 (2022)
  • [27] Yaqing Wang, Xin Tian, Haoyi Xiong, Yueyang Li, Zeyu Chen, Sheng Guo, and Dejing Dou, RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning, Findings of the ACL: NAACL (NAACL Findings) (2022)
  • [28] Yaqing Wang, Song Wang, Yanyan Li, and Dejing Dou, Recognizing Medical Search Query Intent by Few-shot Learning, International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (2022)
  • [29] Z Shen, Y Wang, H Xiong, X Tian, Z Chen, Q Yao, D Dou, PaddleFSL: A General Few-Shot Learning Toolbox in Python, PaddleFSL (2022)
  • [30] Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dongrui Wu, and Dejing Dou, Exploring the Common Principal Subspace of Deep Features in Neural Networks, Machine Learning (MLJ), 111, 1125–1157 (2022)
  • [31] Yaqing Wang, Abulikemu Abuduweili, Quanming Yao, and Dejing Dou, Property-Aware Relation Networks for Few-Shot Molecular Property Prediction (Spotlight), Neural Information Processing Systems (NeurIPS) (2021)
  • [32] Yaqing Wang, Song Wang, Quanming Yao, and Dejing Dou, Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification, Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)
  • [33] Yaqing Wang, Quanming Yao, and James T. Kwok, A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Learning, The Web Conference (TheWebConf/WWW), 1798–1808 (2021)
  • [34] Yaqing Wang, Quanming Yao, James T. Kwok, and Lionel M. Ni, Generalizing from a Few Examples: A Survey on Few-Shot Learning, ACM Computing Surveys (CSUR), 53(3), 1-34 (2020)
  • [35] Yaqing Wang, James T. Kwok, and Lionel M. Ni, Generalized Convolutional Sparse Coding with UnknownNoise, IEEE Transactionson Image Processing (TIP), 29(3), 5386-5395 (2020)
  • [36] Yaqing Wang, Quanming Yao, James T. Kwok, and Lionel M. Ni, Online Convolutional Sparse Coding with Sample-Dependent Dictionary, International Conference on Machine Learning (ICML) (2018)
  • [37] Yaqing Wang, Quanming Yao, James T.Kwok, and Lionel M. Ni, Scalable Online Convolutional Sparse Coding, IEEE Transactions on Image Processing (TIP), 27, 4850-4859 (2018)
  • [38] Yaqing Wang, James T. Kwok, Quanming Yao, and Lionel M. Ni, Zero-shot learning with a partial set of observed attributes, International Joint Conference on Neural Networks (IJCNN) (2017)

 

更新时间: 2026-06-05 18:00:09