| 李鑫 复旦大学智能复杂体系基础理论与关键技术实验室在职博士后 E-mail:li_xin@nudt.edu.cn |
简介
主要研究方向为机器学习与复杂系统，复杂网络与大数据，主要包括复杂动力系统的自动建模、动力学预测、变点检测、以及临界点预测等。
教育经历
2019.09-2024.12 国防科技大学理学院 系统科学专业 博士学位 导师：段晓君教授
2021.10-2022.10 复旦大学智能复杂体系基础理论与关键技术实验室 数学专业 联合培养 导师：林伟教授
2015.09-2019.06 国防科技大学理学院 数学专业 学士学位
工作经历
2024.12-至今 国防科技大学理学院讲师
2025.09-至今 复旦大学智能复杂体系基础理论与关键技术实验室在职博士后
代表成果
1. Xin Li, Qunxi Zhu, Chengli Zhao, et al. Higher-order Granger reservoir computing: simultaneously achieving scalable complex structures inference and accurate dynamics prediction[J]. Nature Communications, 2024, 15(1): 2506.
2. Xin Li, Qunxi Zhu, Chengli Zhao, et al. Tipping point detection using reservoir computing[J]. Research, 2023, 6: 0174.
3. Xin Li, Huichun Li, Xue Zhang, et al. Quantifying the potential of cascade outbreaks via early infected nodes using network percolation[J]. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2024, 34(4).
4. Xin Li, Jingdong Zhang, Qunxi Zhu, et al. From Fourier to Neural ODEs: Flow matching for modeling complex systems. Proceedings of the 41st International Conference on Machine Learning (ICML), Vienna, Austria. PMLR 235, 2024.
5. Xin Li, Chengli Zhao, Xue Zhang, Xiaojun Duan. Symbolic Neural Ordinary Differential Equations. Proceedings of the 38th Association for the Advancement of Artificial Intelligence (AAAI), Philadelphia, Pennsylvania, USA. 2025.
6. Xin Li, Xue Zhang, Chengli Zhao, et al. Identifying highly influential nodes in multilayer networks based on global propagation[J]. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2020, 30(6).
7. 李鑫,李哲民,魏居辉,等.基于特征分离的跨域自适应学习模型[J].计算机研究与发展, 2022, 59(1):13.
8. 李鑫, 赵城利, 刘阳洋. 有限步传播范围期望指标判别节点传播影响力[J]. 物理学报, 2020, 69(2): 28901-028901.
9. Qunxi Zhu, Xin Li, Wei Lin. Leveraging neural differential equations and adaptive delayed feedback to detect unstable periodic orbits based on irregularly sampled time series[J]. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2023, 33(3).（共同一作）
10. Huichun Li, Xin Li, Xue Zhang, et al. Detecting early-warning signals for social emergencies by temporal network sociomarkers[J]. Information Sciences, 2023, 627: 189-204.
