1、基本信息
姓名：张文钧
办公地点：湖北省武汉市洪山区珞喻路152号华中师范大学
专业职称：特任副研究员
博/硕导：硕士生导师
硕士生招生专业：人工智能 计算机科学与技术 电子信息工程
邮箱：wjzhang@ccnu.edu.cn
2、工作经历
2015-09月至2019-06月, 中国地质大学（武汉）计算机学院, 学士学位
2019-09月至2022-06月, 中国地质大学（武汉）计算机学院, 硕士学位
2022-09月至2025-12月, 中国地质大学（武汉）计算机学院, 博士学位
2025-04月至2025-11月, 日本京都大学, 联合培养博士研究生
2025-12月至今, 华中师范大学人工智能教育学部, 特任副研究员
3、研究方向
数据挖掘、机器学习、众包学习、弱监督学习、贝叶斯分类学习
4、科研项目
中央高校基本科研业务费-新进教师项目，XJ2026001301，2026.3-2028.3，在研，主持
国家自然科学基金面上项目，2023.1-2026.12，在研，参与
湖北省揭榜制科技项目，2021.7-2024.6，已结题，参与
中国高校产学研创新基金重点项目，2021.9-2022.8，已结题，参与
教育部人工智能重点实验室开放基金项目，2020.10-2022.9，已结题，参与
企事业单位委托科技项目，2019.4-2020.12，已结题，参与
5、专利成果
朱抗、蒋良孝*、张文钧等，一种基于加权相对密度的众包标记噪声过滤方法，专利号：ZL202210432916.9，授权公告日：2025-5-23
蒋良孝*、李娇、张文钧，一种众包标记真值推理方法、设备及存储设备，专利号：ZL202310386915.X，授权公告日：2025-4-25
蒋良孝*、张文钧、张欢、李超群，一种基于随机森林的伯努利朴素贝叶斯文本分类方法，专利号：ZL202010125450.9，授权公告日：2023-4-7
6、个人荣誉
2025.09: 博士研究生国家奖学金
2025.02: 中国地质大学（武汉）优秀研究生标兵
2024.08: 联合培养博士生中国政府奖学金
2024.06: 中国地质大学（武汉）2022-2024年度优秀共产党员
2023.09: 博士研究生国家奖学金
2023.06: “泰迪杯”第十一届数据挖掘挑战赛国家级三等奖
2023.06: “泰迪杯”第十届数据挖掘挑战赛湖北省一等奖
2023.02: 中国地质大学（武汉）优秀研究生标兵
2022.06: 中国地质大学（武汉）优秀硕士毕业生
2021.09: 硕士研究生国家奖学金
2021.11: 中国地质大学（武汉）第三十二届研究生科技论文报告会一等奖
2020.12: “华为杯”第十七届中国研究生数学建模竞赛二等奖
2019.12: “华为杯”第十六届中国研究生数学建模竞赛三等奖
7、我的学生
王梦恩,硕士研究生,2025年入学(未毕业), 机器学习与数据挖掘, 研一在读
余慰,硕士研究生,2025年入学(未毕业), 机器学习与数据挖掘, 研一在读
沈密,硕士研究生,2025年入学(未毕业), 机器学习与数据挖掘, 研一在读
8、发表论文
L. Yu, W. Zhang, and L. Jiang*. Random Forest-based Weighted Majority Voting for Crowdsourcing. Frontiers of Computer Science, doi: 10.1007/s11704-025-51186-2.
C. Li, L. Jiang*, W. Zhang, L. Yu, and H. Zhang. Instance Correlation Graph-based Naive Bayes. In: Proceedings of the 42nd International Conference on Machine Learning, ICML 2025, PMLR 267: 35021-35033. (CCF-A)
W. Zhang, L. Jiang*, and C. Li. TLLC: Transfer Learning-based Label Completion for Crowdsourcing. In: Proceedings of the 42nd International Conference on Machine Learning, ICML 2025, PMLR 267: 75178-75191. (CCF-A)
T. Wu, L. Jiang*, W. Zhang, and C. Li. Label Distribution Propagation-based Label Completion for Crowdsourcing. In: Proceedings of the 42nd International Conference on Machine Learning, ICML 2025, PMLR 267: 67369-67381. (CCF-A)
J. Li, L. Jiang*, and W. Zhang. Label Consistency-based Ground Truth Inference for Crowdsourcing. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(5): 9408-9421. (CAAI-A)
X. Wu, L. Jiang*, W. Zhang, and C. Li. Worker Similarity-based Label Completion for Crowdsourcing. IEEE Transactions on Big Data, 2025, 11(2): 710-721.
H. Zhang, L. Jiang*, W. Zhang, and G. I. Webb. Dual-View Learning from Crowds. ACM Transactions on Knowledge Discovery from Data, 2025, 19(3): 61.
W. Zhang, L. Jiang*, and C. Li. ELDP: Enhanced Label Distribution Propagation for Crowdsourcing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(3): 1850-1862. (CCF-A)
Q. Ji, L. Jiang*, W. Zhang, and C. Li*. Learning from Crowds by Class-specific Instance Weighting. IEEE Transactions on Emerging Topics in Computational Intelligence, 2025, 9(6): 4015-4025.
W. Zhang, L. Jiang*, and C. Li. KFNN: K-Free Nearest Neighbor For Crowdsourcing. In: Proceedings of the 38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024, Advances in Neural Information Processing Systems 37: 116493-116512. (CCF-A)
W. Zhang, L. Jiang*, and C. Li. IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing. In: Proceedings of the 38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024, Advances in Neural Information Processing Systems 37: 85722-85741. (CCF-A)
B. Yang, L. Jiang*, and W. Zhang. Probabilistic Matrix Factorization-based Three-stage Label Completion for Crowdsourcing. In: Proceedings of the 24th IEEE International Conference on Data Mining, ICDM 2024, pp. 540-549.
J. Li, L. Jiang*, X. Wu, and W. Zhang. Learning from Crowds with Dual-View K-Nearest Neighbor. In: Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence, UAI 2024, PMLR 244: 2238-2249. (CAAI-A)
J. Li, L. Jiang*, C. Li, and W. Zhang. Label Consistency-based Worker Filtering for Crowdsourcing. In: Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence, UAI 2024, PMLR 244: 2226-2237. (CAAI-A)
Z. Chen, L. Jiang*, W. Zhang, and C. Li. Weighted Adversarial Learning from Crowds. IEEE Transactions on Services Computing, 2024, 17(6): 4467-4480. (CCF-A)
W. Zhang, L. Jiang*, Z. Chen, and C. Li. FNNWV: Farthest-Nearest Neighbor-based Weighted Voting for Class-Imbalanced Crowdsourcing. Science China Information Sciences, 2024, 67(10): 202102. (CCF-A)
Y. Hu, L. Jiang*, and W. Zhang. Worker Similarity-based Noise Correction for Crowdsourcing. Information Systems, 2024, 121: 102321.
L. Ren, L. Jiang*, W. Zhang, and C. Li. Label Distribution Similarity-based Noise Correction for Crowdsourcing. Frontiers of Computer Science, 2024, 18(5): 185323.
X. Wu, L. Jiang*, W. Zhang, and C. Li. Three-way Decision-based Noise Correction for Crowdsourcing. International Journal of Approximate Reasoning, 2023, 160: 108973.
Q. Ji, L. Jiang*, and W. Zhang. Instance Weighting-based Noise Correction for Crowdsourcing. In: Proceedings of the 19th International Conference on Intelligent Computing, ICIC 2023, LNAI 14089: 285–297.
Q. Ji, L. Jiang*, and W. Zhang. Dual-View Noise Correction for Crowdsourcing. IEEE Internet of Things Journal, 2023, 10(13): 11804-11812.
H. Zhang, L. Jiang*, W. Zhang, and C. Li. Multi-view Attribute Weighted Naive Bayes. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(7): 7291-7302. (CCF-A)
