梁建青，博士，副教授，硕士生导师。博士毕业于天津大学。主要研究方向为机器学习和图数据挖掘。近年来，在AI、TPAMI、TIP、ICML、NeurIPS、WWW等重要学术刊物上发表学术论文30余篇。获2023年山西省自然科学一等奖，2024年山西省科技创新领域青年拔尖人才，2025年世界人工智能大会青年优秀论文入围奖，2019年天津大学优秀博士学位论文奖，WSDM 2022杰出审稿人奖以及CCML 2017最佳学生论文奖。主持、参与国家自然科学基金青年项目、面上项目、科技部重大项目、国家自然科学基金联合基金重点项目等10余项。申请发明专利 16 项，获得软件著作权登记 10 项。CCF高级会员、CCF 人工智能与模式识别专业委员会委员、CAAI 粒计算与知识发现专业委员会委员，担任人工智能领域国际学术期刊和会议TPAMI、IJCV、ICML、NeurIPS、ICCV、ICLR、KDD、AAAI审稿人。
1. 监督信息受限的多视图图表示学习方法研究，国家自然科学基金面上项目，2024.01-2027.12，主持
2. 面向高维数据的多视图距离度量学习，国家自然科学基金青年项目，2021.01-2023.12，主持
3. 认知计算基础理论与方法研究，科技部科技创新2030—“新一代人工智能”重大项目，2021.1-2024.10，参与
4. 网络大数据分析挖掘的理论与方法，国家自然科学基金联合基金项目，2022.01-2025.12，参与
5. 复杂多视图数据统一表示及分类研究，国家自然科学基金面上项目，2020.1–2023.12，参与
6. 半配对的图像和文本异构迁移学习方法研究，国家自然科学基金青年项目，2018.1–2020.12，参与
7. 面向复杂多视角数据的层次聚类研究，国家自然科学基金青年项目，2017.1–2019.12，参与
8. 大规模异构数据匹配的距离度量学习，国家自然科学基金青年项目，2016.1–2018.12，参与
[1] J Liang, M Chen, X Wei, J Liang*. SCGT: Towards scalable and comprehensive graph transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.
[2] J Liang*, X Wei, Z Li. CL-GCL: Comprehensive and lightweight graph contrastive learning. In Proceedings of the 43rd International Conference on Machine Learning, 2026.
[3] Z Li, J Liang*, Z Wang, X Luo, J Liang. Learning molecular semantic invariant representation with prototype constraint. In Proceedings of the 43rd International Conference on Machine Learning, 2026.
[4] L Wu, S Cheng, Z Wang*, J Liang, P Song, X, J Liang. Multi-scale explainer for graph neural networks. In Proceedings of the 43rd International Conference on Machine Learning, 2026.
[5] Z Wang, J Zhang, C Zhang, S Cheng, J Liang*, P Song. Counterfactual meta-task augmentation for few-shot graph node classification. In Proceedings of the ACM Web Conference, 2026, 4407-4417.
[6] Y Guo, J Liang*, K Yao, Z Guo, J Liang. Graph adversarial defense via hilbert-schmidt independence criterion against influence maximization attacks. In Proceedings of the ACM Web Conference, 2026, 4565-4576.
[7] K Yao, Z Li, J Liang*, J Liang, M Li, F Cao. HyperMixup: Hypergraph-augmented with higher-order information mixup. Advances in Neural Information Processing Systems, 2026, 38, 167109-167129.
[8] C Fang, J Liang*, J Liang, Z Du, F Cao. Point cloud semantic scene completion with prototype-guided transformer. In Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence, 2026, 40 (5): 3822-3830.
[9] Z Zhou, J Liang*, J Liang, Z Du, C Fang. Semantic guided part relation-aware network for point cloud completion. In Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence, 2026, 40 (16): 13871-13879.
[10] J Liang*, Z Li, X Wei, Y Liu, Z Wang. ML2-GCL: Manifold learning inspired lightweight graph contrastive learning. In Proceedings of the 42nd International Conference on Machine Learning, 2025.
[11] Z Wang, X Wang, J Liang*. CSG-ODE: ControlSynth graph ODE for modeling complex evolution of dynamic graphs. In Proceedings of the 42nd International Conference on Machine Learning, 2025.
[12] Z Wang, J Wen, J Liang*. Delay-DSGN: A dynamic spiking graph neural network with delay mechanisms for evolving graph. In Proceedings of the 42nd International Conference on Machine Learning, 2025.
[13] J Cui, Q Yue, J Liang*, J Liang*. Human cognition-inspired hierarchical fuzzy learning machine. In Proceedings of the 42nd International Conference on Machine Learning, 2025.
[14] C Fang, J Liang*, J Liang, H Wang, K Yao, F Cao. Multi-modal point cloud completion with interleaved attention enhanced transformer. In Proceedings of the 34th International Joint Conference on Artificial Intelligence, 2025.
[15] Y Fan, J Cui, J Liang, J Liang*. Open-world semi-supervised learning with class semantic correlations. In Proceedings of the 34th International Joint Conference on Artificial Intelligence, 2025.
[16] Z Li, J Wang, J Liang*, J Cui, X Zhao, J Liang. Uncertainty-guided graph contrastive learning from a unified perspective. In Proceedings of the 34th International Joint Conference on Artificial Intelligence, 2025.
[17] J Liang, X Wei, M Chen, Z Wang, J Liang*. Gnn-transformer cooperative architecture for trustworthy graph contrastive learning. In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, 2025, 39(18): 18667-18675.
[18] Q Yue, J Cui, J Liang*, L Bai*. Class semantic attribute perception guided zero-shot learning. In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, 2025.
[19] Z Wang, J Pan, X Zhao*, J Liang, C Feng, K Yao. Counterfactual task-augmented meta-learning for cold-start sequence recommendation. In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, 2025.
[20] Z Wang, J Guo, J Liang*, J Liang, S Cheng, J Zhang. Graph segmentation and contrastive enhanced explainer for graph neural networks. In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, 2025.
[21] J Liang, M Chen, J Liang*. Graph external attention enhanced transformer. In Proceedings of the 41st International Conference on Machine Learning, 2024, 1191, 29560 –29574.
[22] Z Du, J Liang, J Liang*, K Yao, F Cao. Graph regulation network for point cloud segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, DOI: 10.1109/TPAMI.2024.3400402.
[23] Q Yue, J Cui, L Bai*, J Liang, J Liang. A zero-shot learning boosting framework via concept-constrained clustering. Pattern Recognition, 2023, 109937.
[24] J Liang*, Z Du, J Liang, K Yao, F Cao. Long and short-range dependency graph structure learning framework on point cloud. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, DOI: 10.1109/TPAMI.2023.3298711.
[25] J Cui, J Liang, Q Yue, J Liang*. A general representation learning framework with generalization performance guarantees. In Proceedings of the 40th International Conference on Machine Learning, 2023.
[26] S Tang, K Yao*, J Liang, Z Wang, J Liang. Graph neural networks with interlayer feature representation for image super-resolution. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 2023, 652-660.
[27] X Guo, W Wei*, J Liang, C Dang, J Liang. Metric learning via perturbing hard-to-classify instances. Pattern Recognition, 2022, 132, 108928.
[28] K Yao, J Liang*, J Liang, M Li, F Cao. Multi-view graph convolutional networks with attention mechanism. Artificial Intelligence, 2022, 307, 103708.
[29] J Wang, J Liang*, J Liang, K Yao. GUIDE: Training deep graph neural networks via guided dropout over edges. IEEE Transactions on Neural Networks and Learning Systems, 2022, DOI: 10.1109/TNNLS.2022.3172879.
[30] T Guo, J Liang*, J Liang, GS Xie. Cross-modal propagation network for generalized zero-shot learning. Pattern Recognition Letters, 2022, 159, 125-131.
[31] J Liang, P Zhu*, C Dang, Q Hu*. Semisupervised laplace-regularized multimodality metric learning. IEEE Transactions on Cybernetics, 2022, 52(5): 2955-2967.
[32] J Wang, J Liang*, K Yao, J Liang, D Wang. Graph convolutional autoencoders with co-learning of graph structure and node attributes. Pattern Recognition, 2022, 121, 108215.
[33] J Liang, Q Hu*, C Dang, W Zuo. Weighted graph embedding-based metric learning for kinship verification. IEEE Transactions on Image Processing, 2019, 28(3):1149–1162.
[34] J Liang, Q Hu*, P Zhu, W Wang. Efficient multi-modal geometric mean metric learning. Pattern Recognition, 2018, 75:188–198.
[35] J Liang, Q Hu*, W Wang, Y Han. Semisupervised online multikernel similarity learning for image retrieval. IEEE Transactions on Multimedia, 2017, 19(5): 1077–1089.
[36] 齐忍，朱鹏飞*，梁建青. 混杂数据的多核几何平均度量学习. 软件学报, 2017, 28 (11), 2992-3001.
[37] J Liang, Y Han, Q Hu*. Semi-supervised image clustering with multi-modal information. Multimedia Systems, 2016, 22(2): 149–160.
[38] C Dang*, J Liang, Y Yang. A deterministic annealing algorithm for approximating a solution of the linearly constrained nonconvex quadratic minimization problem. Neural Networks, 2013, 39, 1-11.
[1] 梁建青, 梁吉业. 黎曼空间下的半监督多视图度量学习方法, 中国, ZL 202210847014.1
[2] 梁建青, 张志鑫, 梁吉业. 一种多视图双曲-双曲图表示学习方法, 中国, ZL 202211602476.3
[3] 王智强, 梁吉业, 梁建青. 一种基于概率产生式的社交网络时序链接预测方法及装置, 中国, ZL 202010102869.2
[4] 梁吉业, 李琳, 王智强, 梁建青. 一种基于矩阵分解的事后可解释性推荐方法及装置, 中国, ZL 202010034176.4
[5] 梁建青, 梁吉业. 基于广义多视图图嵌入的亲属关系验证方法, 中国, CN 202210856270.7
[6] 梁建青, 陈敏. 一种图外部注意力引导的多视图图表示学习方法及设备, 中国, CN 202311750481.3
[7] 梁建青, 卫新凯, 陈敏, 梁吉业. 一种GNN 和Transformer 协同的图对比学习方法、系统和设备, 中国, CN 202411435407.7
[8] J Liang, Z Zhang, J Liang. Multi-view hyperbolic-hyperbolic graph representation learning method, 美国, 18/534, 295
[9] J Liang, Min Chen. Method and device for graph external attention (gea)-guided multi-viewgraph representation learning, 美国, 18/975, 371
[10] J Liang, J Liang. Kinship verification method based on generalized multi-view graph embedding, 美国, 18/216, 765
[11] 杜子金, 梁吉业, 梁建青. 一种基于双分支图Transformer的点云补全方法, 中国, CN 202410492712.3
[12] 梁吉业, 杜子金, 梁建青, 王智强, 姚凯旋. 一种基于空间几何感知卷积神经网络的点云形状分析方法, 中国, ZL 202210540037.8
[13] 梁吉业, 杜子金, 梁建青. 一种基于图调控网络的点云分割系统, 中国, ZL 202311197098.X
[14] 梁吉业, 郭宇星, 姚凯旋, 梁建青. 基于特征拓扑融合的黑盒图对抗攻击方法, 中国, CN 202310684810.2
[15] 梁吉业, 杜子金, 梁建青, 姚凯旋. 一种基于远程-短程依赖图学习的点云分类与分割方法, 中国, ZL 202310241163.8
[16] 梁吉业, 李志强, 王杰, 梁建青. 一种基于图对比学习的引文网络节点分类方法及系统, 中国, ZL 202310874661.6
世界人工智能大会青年优秀论文入围奖，2025
CCF中国图机器学习会议杰出海报奖，2025
山西省自然科学一等奖，2023
山西省科技创新领域青年拔尖人才，2024
天津大学优秀博士学位论文奖，2019
WSDM杰出审稿人奖，2022
CCML最佳学生论文奖，2017
学术交流
资源受限条件下的图表示学习方法，CSIG菁英青云论坛第49期，2025.7.25
资源受限条件下的图表示学习方法，CGCKD 女科学家论坛 ，2025.7.30
Graph Representation Learning Methods under Resource Constraints，国际产学研用合作会议暨第五届认知与语义计算国际研讨会，2025.11.10
兴趣爱好
乒乓球，羽毛球，网球，跑步
