最终学历：研究生
研究方向：机器学习与数据挖掘等
电子邮箱：ykx@sxu.edu.cn
最终学位：博士
研究生导师：硕士生导师
联系电话：0351-7010566
姚凯旋，博士，讲师，2023年博士毕业于山西大学计算机与信息技术学院，研究方向为机器学习与数据挖掘。在Artificial Intelligence、Pattern Recognition、Neural Networks、ACM WSDM等国内外期刊和会议发表论文多篇。曾获2022年宝钢教育基金优秀学生奖、山西省优秀博士学位论文奖、2022年CCF优秀大学生学术秀（博士组）二等奖、2023年ACM中国理事会太原分会优秀博士学位论文奖。担任《中国科学：信息科学》、IEEE TIP、IEEE TNNLS、ACM TKDD、Neural Networks、NeurIPS、ICML、ICLR等期刊和会议的审稿人。
[1] 国家自然科学基金青年项目（No. 62406180）, 图神经网络的表达能力与深层模型构造研究, 2025-01 至 2027-12, 主持
[2] 山西省基础研究计划青年项目（No. 202403021212337）, 图神经网络的逼近性与过平滑性研究, 2024-07 至 2027-07, 主持
[3] 科技创新2030-“新一代人工智能”重大项目（No. 2020AAA0106100）, 认知计算基础理论与方法研究, 2020-11 至 2024-10, 参与
[4] 国家自然科学基金联合基金重点项目（No. U21A20473）, 网络大数据分析挖掘的理论与方法, 2022-01-01 至 2025-12-31, 参与
[1] Kaixuan Yao, Jiye Liang, Jianqing Liang, Ming Li, Feilong Cao. Multi-view graph convolutional networks with attention mechanism. Artificial Intelligence. 2022, 307: 103708.
[2] Kaixuan Yao, Feilong Cao, Yee Leung, Jiye Liang. Deep neural network compression through interpretability-based filter pruning. Pattern Recognition. 2021, 119: 108056.
[3] Kaixuan Yao, Zijin Du, Ming Li, Feilong Cao, Jiye Liang. Robust graph neural networks with Dirichlet regularization and residual connection. International Journal of Machine Learning and Cybernetics, 2024.
[4] Shenggui Tang, Kaixuan Yao*, Jianqing Liang, Zhiqiang Wang, Jiye Liang. Graph neural networks with interlayer feature representation for image super-resolution. Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (ACM WSDM). 2023: 652-660.
[5] Feilong Cao, Kaixuan Yao, Jiye Liang. Deconvolutional neural network for image super-resolution. Neural Networks. 2020, 132: 394-404.
[6] Liangliang Wen, Jiye Liang, Kaixuan Yao, Zhiqiang Wang. Black-box adversarial attack on graph neural networks with node voting mechanism. IEEE Transactions on Knowledge and Data Engineering, 2024.
[7] Jiye Liang, Zijin Du, Jianqing Liang, Kaixuan Yao, Feilong Cao. Long and short-range dependency graph structure learning framework on point cloud. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
[8] Zhihao Guo, Feng Wang, Kaixuan Yao, Jiye Liang, Zhiqiang Wang. Multi-scale variational graph autoencoder for link prediction. Proceedings of the Fifteenth ACM international conference on web search and data mining (ACM WSDM). 2022: 334-342.
[9] Jie Wang, Jianqing Liang, Jiye Liang, Kaixuan Yao. GUIDE: Training deep graph neural networks via guided dropout over edges. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(4): 4465-4477.
[10] Jie Wang, Jiye Liang, Kaixuan Yao, Jianqing Liang, Dianhui Wang. Graph convolutional autoencoders with co-learning of graph structure and node attributes. Pattern Recognition, 2022, 121: 108215.