祝恒书 男 中国科学院计算机网络信息中心
电子邮件: hszhu@cnic.cn
通信地址: 北京市海淀区东升南路2号院,中国科学院计算机网络信息中心
个人简介
祝恒书,中国科学院计算机网络信息中心学术副主任、研究员、博士生导师,科学数据智能与创新实验室(DSL)主任,科学数据技术与系统北京市重点实验室首席科学家,入选中国科学院领军人才项目。长期从事人工智能、数据科学及其跨学科应用研究,致力于发展负责任、高效的数据驱动方法与智能技术,推动科学发现与产业创新。曾在百度等知名上市互联网企业从事人工智能研发与技术管理工作,历任多个高级技术管理职务,在产业级技术创新、成果转化与产品研发方面具有丰富经验。在Nature Cities, Nature Communications, TKDE, TOIS, TPAMI, KDD, SIGIR, ICDE, ICML, AAAI等国际顶级学术期刊和会议上发表论文200余篇,谷歌学术引用超20,000次,多次荣获年度最佳论文奖或提名奖。牵头研发了IEEE 3154系列国际标准及多个人工智能领域的国家行业标准,授权国际国内专利近百项。他领导团队在“AI+科学”领域开展了一系列具有国际影响力的工作,主持研发了国际首个从“数据 +模型”双维度出发,面向人工智能赋能科学研究(AI4Science)的综合评价平台“科学地平线”(SciHorizon); 国际首个基于大语言模型的科学数据推荐智能体“科学数据银行AI”(ScienceDB AI);以及面向跨学科研究的通用型AI智能体科学家协作平台“ 科学幻方”(SciMatrix)。他在企业主持研发了全球首套大数据智能化人才管理综合解决方案和众多“智能招聘”相关创新商业化产品,并荣获《哈佛商业评论》“拉姆·查兰管理实践奖”的全场大奖。相关成果被Harvard Business Review、MIT Technology Review、中国日报、科技日报等权威媒体广泛报道。曾荣获教育部自然科学一等奖、中国管理科学学会管理科学奖(学术类)、中国智库索引CTTI年度智库研究优秀成果一等奖、中国人工智能学会优博论文奖、中国科学院百篇优博论文奖、中国科学院院长特别奖,获评北京市高端领军人才正高级工程师、中国计算机学会(CCF)杰出会员,连续入选了美国斯坦福大学评选的“全球前2%顶尖科学家”榜单,并被《麻省理工科技评论》评为“2023年中国智能计算创新人物”。
【研究领域】:人工智能、数据科学
【研究方向】:数据挖掘与知识发现(KDD)、负责任的科学智能(Responsible AI4S)、智能体AI、大模型技术与应用、人才大数据与智能管理
【招生方向】:(学术型/专业型): 计算机应用技术,计算机技术
【个人主页】:https://zhuhengshu.com/
【实验室主页】:https://www.bigdatamining.cn/
【代表性项目】:
教育背景
工作经历
2024~现在,中国科学院计算机网络信息中心,研究员
2019~2024,中国科学院计算机网络信息中心,客座研究员
2022~2024,看准科技集团(BOSS直聘),职业科学实验室(CSL)主任
2014~2022,百度集团,主任架构师,百度人才智库(TIC)主任
学术兼职:
- 香港科技大学(广州),兼任教授(Adjunct Professor)
- 中国计算机学会大数据专家委员会,执行委员
- 中国计算机学会普适计算专业委员会,执行委员
- 中国人工智能学会智能服务专业委员会,委员
- 《数据与计算发展前沿(中英文)》,第二届编委会委员
- Nature njp Artificial Intelligence, Editorial Board Member
- IEEE标准协会(IEEE Standards Association), 人才服务与管理工作组(TSMWG),主席
- IEEE标准协会(IEEE Standards Association), 科学数据工作组(SDWG),主席
代表性成果
最新论著信息:
【Google Scholar】【DBLP】【个人主页】
出版著作:
《迁移学习算法:应用与实践》, 机械工业出版社, 2023-05
代表性论文(会议):
- SciHorizon-DataEVA: An Agentic System to Scalable AI-Readiness Evaluation of Heterogeneous Scientific Data, In Proceedings of the 32nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2026), 2026, 通讯作者
- ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Services, In Proceedings of the 32nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2026), 2026, 通讯作者
- MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios, In Proceedings of the 32nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2026), 2026, 通讯作者
- SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models, Proceedings of the 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2025), 2025, 通讯作者
- From Missteps to Mastery: Enhancing Low-Resource Dense Retrieval through Adaptive Query Generation, Proceedings of the 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2025), 2025, 通讯作者
- Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework, Proceedings of the 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2025), 2025, 通讯作者
- RIGL: A Unified Reciprocal Approach for Tracing the Independent and Group Learning Processes, Proceedings of the 30th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2024), 2024, 通讯作者
- Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning, Proceedings of the 30th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2024), 2024, 通讯作者
- BOSS: A Bilateral Occupational-Suitability-Aware Recommender System for Online Recruitment, Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023, 通讯作者
- RecruitPro: A Pretrained Language Model with Skill-Aware Prompt Learning for Intelligent Recruitment, Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023, 通讯作者
- Talent Demand Forecasting with Attentive Neural Sequential Model, Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2021), 2021, 通讯作者
- Attentive Heterogeneous Graph Embedding for Job Mobility Prediction, Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2021), 2021, 通讯作者
- DuerQuiz: A Personalized Question Recommender System for Intelligent Job Interview, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2019), 2019, 通讯作者
- A Hierarchical Career-Path-Aware Neural Network for Job Mobility Prediction, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2019), 2019, 通讯作者
- The Impact of Person-Organization Fit on Talent Management: A Structure-Aware Convolutional Neural Network Approach, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2019), 2019, 通讯作者
- Exploring the Urban Region-of-Interest through the Analysis of Online Map Search Queries, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2018), 2018, 通讯作者
- Prospecting the Career Development of Talents: A Survival Analysis Perspective, Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2017), 2017, 通讯作者
- Days on Market: Measuring the Liquidity of Real Estate Markets,Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016), 2014, 第一作者
- Mobile App Recommendations with Security and Privacy Awareness, Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2014), 2014, 第一作者
- MIRROR: A Multi-View Reciprocal Recommender System for Online Recruitment, Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024), 2024, 通讯作者
- Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph, Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023), 2023, 通讯作者
- Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach, Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018), 2018 通讯作者
- OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation, Proceedings of 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024), 2024, 通讯作者
- Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking, Proceedings of Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), 2024, 通讯作者
- Topic Modeling Revisited: A Document Graph-based Neural Network Perspective, Proceedings of Thirty-fifth Annual Conference on Neural Information Processing Systems (NeurIPS 2021), 2021, 通讯作者
- Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation, Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021, 通讯作者
- Harnessing Large Language Models for Text-Rich Sequential Recommendation, Proceedings of The Web Conference 2024 (WWW 2024), 2024, 通讯作者
- Variable Interval Time Sequence Modeling for Career Trajectory Prediction: Deep Collaborative Perspective, Proceedings of The Web Conference 2021 (WWW 2021), 2021, 通讯作者
- Cost-Effective and Interpretable Job Skill Recommendation with Deep Reinforcement Learning, Proceedings of The Web Conference 2021 (WWW 2021), 2021, 通讯作者
- Personalized Employee Tranining Course Recommendation with Career Development Awareness, Proceedings of The Web Conference 2020 (WWW 2020), 2020, 通讯作者
- Large-Scale Talent Flow Embedding for Company Competitive Analysis, Proceedings of The Web Conference 2020 (WWW 2020), 2020, 通讯作者
- Large-Scale Talent Flow Forecast with Dynamic Latent Factor Model, Proceedings of The Web Conference 2019 (WWW 2019), 2019, 通讯作者
- Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations, Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), 2024, 通讯作者
- A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction, Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), 2024, 通讯作者
- SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback, Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), 2020, 通讯作者
- Exploiting the Contagious Effect for Employee Turnover Prediction, Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), 2019, 通讯作者
- Measuring the Popularity of Job Skills in Recruitment Market: A Multi-Criteria Approach, Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), 2018, 通讯作者
- Collaborative Company Profiling: Insights from an Employee's Perspective, Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI 2017), 2017, 通讯作者
- Pre-DyGAE: Pre-training Enhanced Dynamic Graph Autoencoder for Occupational Skill Demand Forecasting, Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), 2024, 通讯作者
- Reconciling Cognitive Modeling with Knowledge Forgetting: A Continuous Time-aware Neural Network Approach, Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022), 2022, 通讯作者
- Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness, Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021, 通讯作者
- A Joint Learning Approach to Intelligent Job Interview Assessment, Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), 2018, 通讯作者
- Hierarchical Wi-Fi Trajectory Embedding for Indoor User Mobility Pattern Analysis, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (UbiComp 2023), 2023, 通讯作者
- ResuFormer: Semantic Structure Understanding for Resumes via Multi-Modal Pre-training, Proceedings of the 39th IEEE International Conference on Data Engineering (ICDE 2023), 2023, 通讯作者
- Knowledge Enhanced Person-Job Fit for Talent Recruitment, Proceedings of the 38th IEEE International Conference on Data Engineering (ICDE 2022), 2022, 通讯作者
- DOMFN: A Divergence-Orientated Multi-Modal Fusion Network for Resume Assessment, Proceedings of the 30th ACM International Conference on Multimedia (MM 2022), 2022, 通讯作者
代表性论文(期刊):
- Market-oriented Job Skill Valuation with Cooperative Composition Neural Network, Nature Communications, 2021, 通讯作者
- Large-scale online job search behaviors reveal labor market shifts amid COVID-19, Nature Cities, 2024, 通讯作者
- Scalable intermediate-term earthquake forecasting with multimodal fusion neural networks, Scientific Reports, 2025, 通讯作者
- Rapid Learning of Earthquake Felt Area and Intensity Distribution with Real-time Search Engine Queries, Scientific Reports, 2020, 第一作者/通讯作者
- Evolutionary Modeling Reveals that Value-oriented Knowledge Creation Behaviors Reinvent Jobs, Humanities & Social Sciences Communications, 2025, 通讯作者
- Quasi-Metric Learning for Bilateral Person-Job Fit, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025, 通讯作者
- Exploiting Real-time Search Engine Queries for Earthquake Detection: A Summary of Results, ACM Transactions on Information Systems (ACM TOIS), 2021, 通讯作者
- Towards Unified Representation Learning for Career Mobility Analysis with Trajectory Hypergraph, ACM Transactions on Information Systems (ACM TOIS), 2024, 通讯作者
- Market-aware Long-term Job Skill Recommendation with Explainable Deep Reinforcement Learning, ACM Transactions on Information Systems (ACM TOIS), 2024, 通讯作者
- SetRank: A Setwise Bayesian Approach for Collaborative Ranking in Recommender System, ACM Transactions on Information Systems (ACM TOIS), 2023, 通讯作者
- Automatic Skill-oriented Question Generation and Recommendation for Intelligent Job Interviews, ACM Transactions on Information Systems (ACM TOIS), 2023, 通讯作者
- Contextualized Knowledge Graph Embedding for Explainable Talent Training Course Recommendation, ACM Transactions on Information Systems (ACM TOIS), 2023, 通讯作者
- Joint Representation Learning with Relation-enhanced Topic Models for Intelligent Job Interview Assessment, ACM Transactions on Information Systems (ACM TOIS), 2021, 通讯作者
- Personalized and Explainable Employee Training Course Recommendations: A Bayesian Variational Approach, ACM Transactions on Information Systems (ACM TOIS), 2021, 通讯作者
- Enhancing Employer Brand Evaluation with Collaborative Topic Regression Models, ACM Transactions on Information Systems (ACM TOIS), 2020, 通讯作者
- An Enhanced Neural Network Approach to Person-Job Fit in Talent Recruitment, ACM Transactions on Information Systems (ACM TOIS), 2020, 通讯作者
- University Evaluation Through Graduate Employment Prediction: An Influence Based Graph Autoencoder Approach, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2024, 通讯作者
- Bilateral Multi-Behavior Modeling for Reciprocal Recommendation in Online Recruitment, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2024, 通讯作者
- Towards Automatic Job Description Generation with Capability-Aware Neural Networks, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2022, 通讯作者
- MANE: Organizational Network Embedding with Multiplex Attentive Neural Networks, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2022, 通讯作者
- Modeling the Impact of Person-Organization Fit on Talent Management with Structure-Aware Attentive Neural Networks, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2021, 通讯作者
- What is Market Talking about Market-oriented Prospect Analysis for Entrepreneur Fundraising, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2022, 通讯作者
- Discovery of Ranking Fraud for Mobile Apps,IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2015, 第一作者
- COTR: Efficient Job Task Recognition for Occupational Information Systems with Class-Incremental Learning, ACM Transactions on Management Information Systems (ACM TMIS), 2025, 通讯作者
- Examination Process Modeling for Intelligent Patent Management: A Multi-aspect Neural Sequential Approach, ACM Transactions on Management Information Systems (ACM TMIS), 2025, 通讯作者
- Exploiting Connections among Personality, Job Position, and Work Behavior: Evidence from Joint Bayesian Learning, ACM Transactions on Management Information Systems (ACM TMIS), 2023, 通讯作者
- Exploiting Networks Fusion for Organizational Turnover Prediction, ACM Transactions on Management Information Systems (ACM TMIS), 2021, 通讯作者
- Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning,ACM Transactions on Management Information Systems (ACM TMIS), 2018, 通讯作者
- Who will Win the Data Science Competition? Insights from KDD Cup 2019 and Beyond, ACM Transactions on Knowledge Discovery from Data (ACM TKDD), 2022, 通讯作者
- Handling Over-Smoothing and Over-Squashing in Graph Convolution with Maximization Operation, IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024, 通讯作者
- Popularity Modeling for Mobile Apps: A Sequential Approach,IEEE Transactions on Cybernetics (IEEE TCYB), 2015, 第一作者
- Mobile App Classification with Enriched Contextual Information,IEEE Transactions on Mobile Computing (IEEE TMC), 2014, 第一作者
- Mining Mobile User Preferences for Personalized Context-Aware Recommendation,ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2014, 第一作者
- A Survey on Large Language Models for Recommendation, World Wide Web, 2024, 通讯作者
- Fine-Grained Job Salary Benchmarking with a Nonparametric Dirichlet-process-based Latent Factor Model, INFORMS Journal on Computing (INFORMS JOC), 2022, 通讯作者
- EL-Picker:基于集成学习的余震P波初动实时拾取方法, 《中国科学: 信息科学》, 2020, 通讯作者
- 基于知识图谱的推荐系统研究综述, 《中国科学: 信息科学》, 2020, 通讯作者
指导学生
在读研究生
- 刘典玉(2025级博士):KDD-2026
- 李金鹏(2025级硕士):ACL-2026 Findings
- 侯羽飞(2026级硕转博):KDD-2026
- 齐兆远(2026级硕转博)
- 蔡旭(2026级直博)
- 宋知恒(2026级硕士):KDD-2026
- 刘彥志(2026级硕士)
联合培养:
- 王志高远(港科广AI Thrust,2023级直博):ICML-2025
- 崔淑婷(港科广AI Thrust,2024级直博):ACM TMIS
部分已毕业联培博士/实习生
- 孟庆欣(2020年Rutgers University博士毕业),宁波诺丁汉大学,助理教授
- 滕铭飞(2021年Rutgers University博士毕业),Amazon, Applied Scientist
- 秦川(2021年中国科学技术大学博士毕业),中国科学院计算机网络信息中心,副研究员(中国科学院院长优秀奖,中科院BR计划B类择优)
- 王超(2022年中国科学技术大学博士毕业),中国科学技术大学,副教授(中国计算机学会优博)
- 张乐(2022年中国科学技术大学博士毕业),百度研究院,资深研究员
- 孙莹(2022年中国科学院计算所博士毕业),国防科技大学,副教授(中国计算机学会优博)
- 江珊(2022年天津大学博士毕业),武汉理工大学,助理教授
- 张琦(2023年中国科学技术大学博士毕业),上海人工智能实验室,青年研究员
- 申大忠(2023年中国科学技术大学博士毕业),南京航空航天大学,副教授
- 成一航(2023年天津大学博士毕业),中国科学院计算机网络信息中心,博士后研究员(中科院特别研究助理)
- 武晗(2023年中国科学技术大学博士毕业),合肥工业大学,博士后研究员
- 郑值(2024年中国科学技术大学博士毕业),中国科学技术大学,博士后研究员(中国中文信息学会优博)
- 韩笑(2025年香港城市大学博士毕业),浙江工业大学,特聘研究员
- 魏馨(2025年天津大学博士毕业),北京工业大学,助理教授
- 叶雨扬(2025年Rutgers University博士毕业),TikTok,Research Scientist