※教师简介

杨山田，现任西南财经大学计算机与人工智能学院讲师、硕士生导师。2022年毕业于电子科技大学，获得工学博士学位。杨山田博士的主要研究方向涉及Reinforcement Learning, 大模型（LLM）, Multi-agent Learning和因果推理, 及其在Traffic Signal Control, Autonomous Driving, 金融量化交易，资产组合投资等相关工程控制系统中的应用，在国际期刊、学术会议等发表10余篇学术论文，包括Information Fusion、Pattern Recognition、Neural Networks、TNNLS、AAAI、Information Science等。担任IEEE Transactions On Intelligent Transportation Systems、 Information Fusion、Pattern Recognition、Information Science、Neural Networks 和 IEEE Transactions on Cybernetics、Engineering Applications Of Artificial Intelligence、IET Intelligent Transport Systems等多个SCI期刊的审稿人; DASC(2020-2021)国际会议的技术委员会委员；American Journal of Neural Networks and Applications编委会委员；American Journal of Information Science and Technology(AJIST) 编委会委员；IEEE Technical Committee on Hyper-Intelligence委员；International Conference on Computational and Mathematical Methods in Engineering (CMME2023) 编委会委员，以及 International Conference on Advances in Computer Science and Engineering Technology (ACSE2023) 技术委员会委员。

※研究领域

强化学习+LLM

可信人工智能

  智能金融

※讲授课程

机器学习、强化学习、强化学习原理与应用、统计建模方法与应用、人工智能导论。

※研究成果(注： *表示通讯作者)

[1] Shantian Yang*, Wenyang Deng, Zheng Zeng, Bo Yang, AC-HGL: Heterogeneous Graph Representation Learning through Adaptive Correlation for Stock Movement Prediction, Pattern Recognition, 2026, 113605, https://doi.org/10.1016/j.patcog.2026.113605. (SCI一区，Top期刊)

[2] Ran Tao, Qiugang Zhan, Shantian Yang, Xiurui Xie, Qi Tian, Guisong Liu. SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning. AAAI 2026. (CCF-A)

[3] Zhengyi Li, Zhongfeng Kang, Yutong Wang, Xinyu Kang, Shantian Yang, Qinghua Zhao. ResKANNet: A residual Kolmogorov-Arnold network with multi-scale attention for brain tumor segmentation. Neurocomputing, 664 (2026) 132062. (SCI一区，Top期刊).

[4] Qiugang Zhan, Jinbo Cao, Xiurui Xie, Huajin Tang, Malu Zhang, Shantian Yang, and Guisong Liu. SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning. IEEE Transactions on Neural Networks and Learning Systems, 2025. (SCI一区，Top期刊).

[5] Shantian Yang*, Bo Yang, Zheng Zeng, Zhongfeng Kang. Causal Inference Multi-Agent Reinforcement Learning for Traffic Signal Control, Information Fusion, 2023, https://doi.org/10.1016/j.inffus.2023.02.009. (SCI一区，Top期刊).

[6] Shantian Yang*. Hierarchical graph multi-agent reinforcement learning for traffic signal control. Information Sciences, 634:55-72, 2023.

[7] Shantian Yang*. Deep reinforcement learning for portfolio management. Knowledge-Based System, 278, art No. 110905, 2023.

[8] Shantian Yang* and Bo Yang. An Inductive Heterogeneous Graph Attention-based Multi-agent Deep Graph Infomax Algorithm for Adaptive Traffic Signal Control. Information Fusion, 88:249-262, 2022. https://doi.org/10.1016/j.inffus.2022.08.001. (SCI一区，Top期刊).

[9] Shantian Yang*, Bo Yang, Zhongfeng Kang, Lihui Deng. IHG-MA: Inductive heterogeneous graph multi-agent reinforcement learning for multi-intersection traffic signal control, Neural Networks 139, 265-277, 2021. https://doi.org/10.1016/j.neunet.2021.03.015. (SCI一区，Top期刊，CCF-B).

[10] Shantian Yang* and Bo Yang, A semi-decentralized feudal multi-agent learned-goal algorithm for multi-intersection traffic signal control, Knowledge-Based System, 213, art No. 06708, Dec. 2021. https://doi.org/10.1016/j.knosys.2020.106708. (SCI一区，Top期刊, CCF-C).

[11] Shantian Yang, Bo Yang, Hau-san Wong, Zhongfeng Kang. Cooperative traffic signal control using Multi-step return and Off-policy Asynchronous Advantage Actor-Critic Graph algorithm. Knowledge-Based Systems, 183, art No. 104855, 2019. https://doi.org/10.1016/j.knosys.2019.07.026. (SCI一区，Top期刊).

[12] Shantian Yang and Bo Yang*. A Meta Multi-agent Reinforcement Learning Algorithm for Multi-intersection Traffic Signal Control. IEEE Intl Conf on Depend., Autono. and Secure Compu., pp. 18-25, 2021.

[13] Lihui Deng, Bo Yang*, Zhongfeng Kang, Shantian Yang and Shihu Wu. A Noisy Label and Negative Sample Robust Loss Function for DNN-based Distant Supervised Relation Extraction. Neural Networks, 139, 358-370, 2021.

[14] Zhongfeng Kang, Bo Yang*, Mads Nielsen, Lihui Deng, Shantian Yang. A Buffered Online Transfer Learning Algorithm with Multi-layer Network. Neurocomputing, 488, 581-597, 2022.

[15] Zhongfeng Kang, Bo Yang*, Shantian Yang. Online transfer learning with multiple source domains for multi-class classification. Knowledge-Based Systems, 190, 105149, 2019.

主要科研项目

(1) “基于可解释强化学习的组合投资算法研究(项目号: JBK23YJ26)”，中央高校基本科研业务费专项资金-西南财经大学引进人才科研启动资助项目，2万元，2023.1-2023.12，主持，完成。

(2) “基于图的分布式强化学习的交通信号控制算法研究”(项目号: JBK2406079), 中央高校基本科研业务费专项资金-西南财经大学引进人才科研启动资助项目，2万元，2024.1-2024.12，主持，完成。

(3) “面向在线学习的基于 SAF 的推荐模型研究 (项目号: 61977013)” , 国家自然科学基金，面上项目, 50 万元， 2020.1-2023.12，主研，在研。

(4) “基于梯度提升深度森林的网络教育平台中的推荐系统研究 (项目号: 2019YJ0164)” ,10W 元, 四川省科技厅， 2019.1-2021.1，主研，结题。

(5) “公共服务政策智能推送关键技术研究与原型系统研发 (项目号 190241)” , CECT 大数据研究工程公司， 75 万元, 2019.5-2020.10，主研，结题。

(6) “基于脉冲编码的类脑联邦学习方法研究 (项目号: 2023110040)” , 国家自然科学基金，面上项目, 50 万元， 2024.1-2027.12，主研，在研。