Welcome to Network Science and Graph Learning (NSGL) Lab
欢迎访问 网络科学与图学习实验室 主页
[实验室简介]
本实验室的主要研究方向包括机器学习、图机器学习、进化计算等,同时利用这些智能方法解决网络系统中的问题,包括一般网络、通信网络、工程网络、社交网络等。在网络科学方面,我们主要研究网络的可控性 (controllability)、连通性 (connectivity) 和通信能力 (communication capabilities),以及它们在恶意攻击下的鲁棒性 (robustness, 也翻译作韧性)。
我们的研究课题主要包括:
- 使用 GNN、图学习、强化学习、或其他计算智能技术进行智能体网络优化布局;
- 攻防视角下,结合智能方法评估网络鲁棒性,并优化拓扑增强稳健性;
- 图学习和图分类。
欢迎对复杂网络、(图)机器学习、优化算法及应用 等研究课题感兴趣的同学加入我们实验室。
欢迎通过电子邮件 lou.yang@hotmail.com 询问与交流。
[人才培养]
目前我们课题组从2021年至今已经培养了九名硕士研究生,包括七名已经毕业的硕士研究生 (其中两名继续攻读博士学位),两名在读的硕士研究生:
- 黄文丽,2023级,研究方向: 复杂网络与图机器学习
- 陈亮,2023级,研究方向: 复杂网络与图机器学习
- 吴成沛,2024年毕业,获国家奖学金、省级优秀毕业生,现于四川大学攻读博士学位。
- 武瑞梓,2022年毕业,获国家奖学金、省级优秀毕业生,现于电子科技大学攻读博士学位。
[实验室主要论文]
-
new
C. Wu,
Y. Lou*,
J. Li, L. Wang, S. Xie,
and G. Chen,
"A Multitask Network Robustness Analysis System Based on the Graph Isomorphism Network,"
IEEE Transactions on Cybernetics,
vol. 54, no. 11, pp. 6630–6642; doi:10.1109/TCYB.2024.3422430 (2024) [Open Access]
[Impact Factor = 9.4]
- Y. Lou*, C. Wu, J. Li, L. Wang, and G. Chen, "Network Robustness Prediction: Influence of Training Data Distributions,"
IEEE Transactions on Neural Networks and Learning Systems,
vol. 35, no. 10, pp. 13496–13507; doi:10.1109/TNNLS.2023.3269753 (2024)
[Impact Factor = 10.2]
- Y. Lou*, R. Wu, J. Li, L. Wang, X. Li, and G. Chen, "A Learning Convolutional Neural Network Approach for Network Robustness Prediction,"
IEEE Transactions on Cybernetics,
vol. 53, no. 7, pp. 4531–4544; doi:10.1109/TCYB.2022.3207878 (2023)
[Impact Factor = 9.4]
- Y. Lou*, L. Wang, and G. Chen, "Structural Robustness of Complex Networks: A Survey of A Posteriori Measures,"
IEEE Circuits and Systems Magazine,
vol. 23, no. 1, pp. 12–35; doi:10.1109/MCAS.2023.3236659 (2023)
[Impact Factor = 5.6]
- Y. Lou, Y. He, L. Wang, and G. Chen, "Predicting Network Controllability Robustness: A Convolutional Neural Network Approach,"
IEEE Transactions on Cybernetics,
vol. 52, no. 5, pp. 4052–4063; doi:10.1109/TCYB.2020.3013251 (2022)
[Impact Factor = 9.4]- Y. Lou, Y. He, L. Wang, K.F. Tsang, and G. Chen, "Knowledge-Based Prediction of Network Controllability Robustness,"
IEEE Transactions on Neural Networks and Learning Systems,
vol. 33, no. 10, pp. 5739–5750; doi:10.1109/TNNLS.2021.3071367 (2022)
[Impact Factor = 10.2]
- 楼洋, 李均利, 李升, 邓浩, "复杂网络能控性鲁棒性研究进展"
自动化学报,
vol. 48, no. 10, pp. 2374–2391; doi:10.16383/j.aas.c200916 (2022) (in Chinese)
- Y. Lou*, S.Y. Yuen, and G. Chen, "Non-revisiting Stochastic Search Revisited: Results, Perspectives, and Future Directions,"
Swarm and Evolutionary Computation,
vol. 61, 100828; doi:10.1016/j.swevo.2020.100828 (2021)
[Impact Factor = 8.2]
- Y. Lou, R. Wu, J.Li, L. Wang, and G. Chen, "A Convolutional Neural Network Approach to Predicting Network Connectedness Robustness"
IEEE Transactions on Network Science and Engineering,
vol. 8, no. 4, 3209–3219; doi:10.1109/TNSE.2021.3107186 (2021)
[Impact Factor = 6.7]
- Y. Lou, Lin Wang, and Guanrong Chen, "Enhancing Controllability Robustness of q-Snapback Networks Through Re-directing Edges,"
Research,
vol. 2019, 7857534; doi:10.34133/2019/7857534 (2019)
[Impact Factor = 8.5]
- Y. Lou*, C. Wu, J. Li, L. Wang, and G. Chen, "Network Robustness Prediction: Influence of Training Data Distributions,"
[实验室地址]
- 成都市成龙大道二段1819号
- 四川师范大学成龙校区
- 邮编: 610101