您现在的位置: 首页 » 团队队伍 » 教研系列 » 按名字 » G » 正文

团队队伍

G

高军

职称:教授

研究所:数据科学与工程研究所

研究领域:图数据分析和学习、AI+DB

办公电话:86-10-6275 5825

电子邮件:gaojunpku.edu.cn

 

主要研究方向

目前的研究重点在于深度图神经网络、强化学习、语言模型等应用研究,尤其是深度网络和数据管理技术的结合、和社交网络分析的结合,和异常分析的结合。

具体包括:

  • 图中社区分析、异常节点发现、节点布局

  • AI生成数据库执行计划,调度批查询

  • 大模型下的结构化数据理解,数据集成


招收博士研究生

责任心,动手能力,科研敏感度,积极向上,时间投入


科研课题

  • 自然基金课题,基于异构图神经网络的网络空间行为分析,2023-2026

  • 北大-电信合作项目,数据编织关键技术,2023.1-2023.12

  • 北大-华为合作项目,基于强化学习的查询调度,2023.1-2023.12

  • 北大-中兴合作项目,自适应性数据库学习优化器,2022.11-2023.11

  • 北大-中兴合作项目,数据库学习优化器,2021.11-2022.11

  • 北大国家重点研发课题,基于图神经网络的社交网络分析,2019-2021

  • 国家重点研发课题,基于图神经网络的社交网络分析,2019-2021

  • 之江实验室开放项目,基于图神经网络的异常实体发现,2019-2021

  • 自然基金重点课题,新型数据管理系统,2019-2023

  • 北大-阿里巴巴合作项目,多智能体机器学习,2019.3-2020.3


发表论文(2000-)

  • Tianyi Chen, Jun Gao, Hedui Chen, Yaofen Tu. LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans. In Proc of VLDB 2023

  • Jianzun Chen, Yikuan Xia, Jun Gao. CommunityAF: An Example-based Community Search Method via Autoregressive Flow. In Proc of VLDB 2023

  • Jialin Wang, Xiaoru Qu, Jinze Bai, Zhao Li, Ji Zhang, Jun Gao: SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning. IEEE Trans. Knowl. Data Eng. 35(5): 5216-5229 (2023)

  • Hao Miao, Jiazun Chen, Yang Lin, Mo Xu, Yinjun Han, Jun Gao: JG2Time: A Learned Time Estimator for Join Operators Based on Heterogeneous Join-Graphs. DASFAA (1) 2023: 132-147

  • Jiazun Chen, Jun Gao, Bin Cui: ICS-GNN+: lightweight interactive community search via graph neural network. VLDB J. 32(2): 447-467 (2023)

  • Li Zheng, Zhao Li, Jun Gao, Zhenpeng Li, Jia Wu, Chuan Zhou: Domain Adaptation for Anomaly Detection on Heterogeneous Graphs in E-Commerce. ECIR (2) 2023: 304-318

  • Zhao Li, Junshuai Song, Zehong Hu, Zhen Wang, Jun Gao: Constrained Dual-Level Bandit for Personalized Impression Regulation in Online Ranking Systems. ACM Trans. Knowl. Discov. Data 16(2): 23:1-23:23 (2022)

  • Wentao Zhang, Zeang Sheng, Ziqi Yin, Yuezihan Jiang, Yikuan Xia, Jun Gao, Zhi Yang, Bin Cui: Model Degradation Hinders Deep Graph Neural Networks. KDD 2022: 2493-2503

  • Jiazun Chen, Jun Gao: VICS-GNN: A Visual Interactive System for Community Search via Graph Neural Network. ICDE 2022: 3150-3153

  • Junshuai Song, Xiaoru Qu, Zehong Hu, Zhao Li, Jun Gao, Ji Zhang: A subgraph-based knowledge reasoning method for collective fraud detection in E-commerce. Neurocomputing 461: 587-597 (2021)

  • Jun Gao, Jiazun Chen, Zhao Li, and Ji Zhang. ICS-GNN: Lightweight Interactive Community Search via Graph Neural Network. PVLDB, 14(6):1006 - 1018, 2021.

  • Yikuan Xia, Jun Gao, Bin Cui: iMap: Incremental Node Mapping between Large Graphs Using GNN. CIKM 2021: 2191-2200

  • Li Zheng, Jun Gao, Zhao Li, Ji Zhang: AdaBoosting Clusters on Graph Neural Networks. ICDM 2021: 1523-1528

  • Jinze Bai, Jialin Wang, Zhao Li, Donghui Ding, Ji Zhang, Jun Gao. ATJ-Net: Auto-Table-Join Network for Automatic Learning on Relational Databases. In Proc. of WWW 2021

  • Xiaoru Qu, Zhao Li, Jialin Wang, Zhipeng Zhang, Pengcheng Zou, Junxiao Jiang, Jiaming Huang, Rong Xiao, Ji Zhang, Jun Gao*: Category-aware Graph Neural Networks for Improving E-commerce Review Helpfulness Prediction. In Proc. of CIKM, 2020, Pages 2693-2700.

  • Jinze Bai, Jialin Wang, Zhao Li, Donghui Ding, Jiaming Huang, Pengrui Hui, Jun Gao, Ji Zhang, and Zujie Ren. Recommendation on Heterogeneous Information Network with Type-sensitive Sampling. In Proc. of DASFAA, 2020, Pages 673-684. CCF B

  • Junshuai Song, Zhao Li, Zehong Hu, Yucheng Wu, Zhenpeng Li, Jian Li and Jun Gao. PoisonRec: An Adaptive Data Poisoning Framework for Attacking Black-box Recommender Systems. In Proc of ICDE 2020


负责课程

  • 数据库概念,本科生实验班

  • 数据库原理与技术 研究生课程


部分毕业员工

  • 周畅:阿里巴巴(阿里星)

  • 白金泽:阿里巴巴(阿里星)

  • 宋军帅:腾讯

  • 郑力:腾讯

  • 王佳麟:腾讯


目前在读研究生

  • 屈笑如:博士生,评价文本相关分析技术,CIKM20, TKDE23(共一)

  • 陈嘉尊:博士生,社交网络图社区分析, VLDB21,ICDE 23, VLDB23, VLDBJ23

  • 夏逸宽  博士生,实体映射和集成, CIKM21

  • 苗浩:硕士生,图数据异常分析, DASFAA 23

  • 陈天异:博士生,学习型查询优化器, VLDB 23

  • 邱而沐:博士生,数据模式理解

  • 刘溯晨:博士生,学习型查询优化器

  • 许辰昊:博士生,学习型查询调度器