耿阳李敖

基本信息

教育背景

2019.10 - 2020.11    美国匹兹堡大学，时空数据挖掘，导师：Prof. Heng Huang

2018.03 - 2018.08    台湾清华大学，凸优化理论与应用，导师：祁忠勇 教授

2015.09 - 2021.06    北京交通大学，计算机科学与技术，博士（硕博连读），导师：李清勇 教授

2010.09 - 2014.07    郑州大学，信息管理与信息系统，本科

工作经历

2023 - 今        北京交通大学，气象时空数据挖掘与大模型，讲师

2021 - 2023    清华大学，图神经网络与大模型，博士后，合作导师：唐杰 教授

研究方向

• 计算机技术
• 软件工程
• 大数据技术与工程
• 人工智能
• 机器学习与认知计算
• 智能感知与具身智能
• 新一代电子信息技术

招生专业

• 计算机技术硕士
• 软件工程硕士
• 大数据技术与工程硕士
• 人工智能硕士
• 计算机科学与技术硕士
• 新一代电子信息技术（含量子技术等）硕士

科研项目

教学工作

论文/期刊

代表性期刊论文：

1. Yangli-ao Geng, Chong-Yung Ch, Wenju Sun, et al., Disentangling Clusters from Non-Euclidean Data via Graph Frequency Reorganization. Information Sciences, 120288, 2024.
   
2. Wenju Sun, Qingyong Li, Jing Zhang, Wen Wang, Yangli-ao Geng*, A zero-shot learning framework via cluster-prototype matching. Pattern Recognition, vol. 140, 109561, 2023.
3. Wenju Sun, Qingyong Li, Jing Zhang, Wen Wang, YangLi-ao Geng*, Class Incremental Learning based on Identically Distributed Parallel One-Class Classifiers. Neurocomputing, vol. 556, 126579, 2023.
4. Jing Zhang, Qingyong Li, Yangli-ao Geng, Qingyong Li, et al., A zero-shot learning framework via cluster-prototype matching. Pattern Recognition, vol. 124, 10846, 2022.
5. Jing Zhang, Yangli-ao Geng, Wen Wang, Wenju Sun, Zhirong Yang, Qingyong Li. Distribution and gradient constrained embedding model for zero-shot learning with fewer seen samples. Knowledge-Based Systems, vol. 251, 109218, 2022.
6. Xinyuan Zhou, Yangli-ao Geng, Haomin Yu, Qingyong Li, Liangtao Xu, Wen Yao, Dong Zheng, Yijun Zhang. LightNet+: A dual-source lightning forecasting network with bi-direction spatiotemporal transformation. Applied Intelligence, vol. 52, no. 10, pp. 11147-11159, 2022.
7. Yangli-ao Geng, Qingyong Li, Tianyang Lin, et al., A deep learning framework for lightning forecasting with multi‐source spatiotemporal data. Quarterly Journal of the Royal Meteorological Society, vol. 147, no. 741, pp. 4048-4062, 2021.
8. Yangli-ao Geng, Qingyong Li, Mingfei Liang, et al., Local-Density subspace distributed clustering for high-dimensional data. IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 31, no. 8, pp. 1799-1814, 2020.
9. Haomin Yu, Qingyong Li, Rao Wang, Zechuan Chen, Yingjun Zhang, Yangli-ao Geng, et al. A deep calibration method for low-cost air monitoring sensors with multilevel sequence modeling. IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 9, pp. 7167-7179, 2020.
10. Chen Huang, Andreas F Molisch, Yangli-ao Geng, et al. Trajectory-joint clustering algorithm for time-varying channel modeling. IEEE Transactions on Vehicular Technology, vol. 69, no. 1, pp. 1041-1045, 2019.
11. Yangli-ao Geng, Qingyong Li, Rong Zheng, et al., RECOME: A new density-based clustering algorithm using relative KNN kernel density, Information Sciences, vol. 436-437, pp. 13–30, 2018.
12. Chen Huang, Ruisi He, Zhangdui Zhong, Bo Ai, Yangli-ao Geng, et al. A power-angle-spectrum based clustering and tracking algorithm for time-varying radio channels. IEEE Transactions on Vehicular Technology, vol. 68, no. 1, pp. 291-305, 2018.
13. Haomin Yu, Qingyong Li, Yunqiang Tan, Jinrui Gan, Jianzhu Wang, Yangli-ao Geng, et al. A coarse-to-fine model for rail surface defect detection. IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 3, pp. 656-666, 2018.
14. Ruisi He, Qingyong Li, Bo Ai, Yangli-ao Geng, et al. A kernel-power-density-based algorithm for channel multipath components clustering. IEEE Transactions on Wireless Communications, vol. 16, no. 11, pp. 7138-7151, 2017.

代表性会议论文：

1. Wenju Sun, Qingyong Li, Jing Zhang, Wen Wang, Yangli-ao Geng*. Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
2. Zhen Yang, Tinglin Huang, Ming Ding, Yuxiao Dong, Rex Ying, Yukuo Cen, Yangliao Geng, and Jie Tang. BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023.
3. Ming Zhou, Dan Zhang, Yuandong Wang, Yangli-ao Geng, Jie Tang. Detecting Social Bot on the Fly using Contrastive Learning. ACM International Conference on Information and Knowledge Management (CIKM), 2023.
4. Dong Li, Haomin Yu, Yangli-ao Geng, Xiaobao Li, Qingyong Li. Ddgnet: A dual-stage dynamic spatio-temporal graph network for pm 2.5 forecasting. IEEE International Conference on Big Data, 2021.
5. Yangli-ao Geng, Qingyong Li, Tianyang Lin, Jing Zhang, Liangtao Xu, Wen Yao, Dong Zheng, Weitao Lyu, Heng Huang. A heterogeneous spatiotemporal network for lightning prediction. IEEE international conference on data mining (ICDM), 2020.
6. Haomin Yu, Qingyong Li, Yangli-ao Geng, Yingjun Zhang, Zhi Wei. AirNet: A calibration model for low-cost air monitoring sensors using dual sequence encoder networks, AAAI Conference on Artificial Intelligence. 2020.
7. Jing Zhang, Yangli-ao Geng, Qingyong Li, Chuan Shi. More than one: A cluster-prototype matching framework for zero-shot learning. ACM International Conference on Information & Knowledge Management (CIKM), 2020.
8. Yangli-ao Geng, Qingyong Li, Tianyang Lin, Lei Jiang, Liangtao Xu, Dong Zheng, Wen Yao, Weitao Lyu, Yijun Zhang. Lightnet: A dual spatiotemporal encoder network model for lightning prediction. ACM SIGKDD international conference on knowledge discovery & data mining (KDD), 2019.
9. Mingfei Liang, Qingyong Li, Yangli-ao Geng, Jianzhu Wang, Zhi Wei. REMOLD: an efficient model-based clustering algorithm for large datasets with spark. IEEE International Conference on Parallel and Distributed Systems (ICPADS), 2017.
10. Ruisi He, Qingyong Li, Bo Ai, Yangli-ao Geng, Andreas F Molisch, Vinod Kristem, Zhangdui Zhong, Jian Yu. An automatic clustering algorithm for multipath components based on kernel-power-density. IEEE Wireless Communications and Networking Conference (WCNC), 2017.

专著/译著

专利

唐杰, 耿阳李敖, 东昱晓. 面向学术网络节点分类方法和装置. 申请号：CN202311064423

唐杰, 张丹, 耿阳李敖, 东昱晓. 一种基于双重对比学习的物品推荐方法及装置. 申请号:  CN202310521595

何睿斯, 艾渤, 李清勇, 王琦, 耿阳李敖, 陈瑞凤, 钟章队, 于剑. 一种基于核功率密度的无线信道多径分簇方法. 申请号: CN201610978957

软件著作权

获奖与荣誉

教育部高教司重点领域教学资源建设优秀专家，2023

34届国际无线电科学联盟青年科学家奖，2021

中国铁道学会科学技术奖二等奖，2020

北京交通大学教学成果一等奖，2020

国家留学基金委公派出国奖学金，2019

社会兼职