蔡佳，博士，教授，博士生导师。2009年10月博士毕业于香港城市大学数学系，师从德国洪堡基金、国家杰青获得者、《Analysis & Applications》期刊总编、澳大利亚悉尼大学教授周定轩。2019年破格晋升为教授，同年12月入选广东省省级人才计划，现担任国家自然科学基金评审专家，广东省自然科学基金评审专家，教育部科技管理系统入库专家，湖北省科技厅项目评审专家，江苏省科技厅项目评审专家，黑龙江省科技厅项目评审专家。主持和承担国家自科(青年、面上)、国家社科重点项目、香港资助局科研项目，国家统计局重点项目，广东省自然科学基金，教育部人文社科，广州市科技计划等合计20余项，其中主持国家自然科学金3项(已完成2项)。已在国内外著名期刊《Applied and Computational Harmonic Analysis》，《IEEE Transactions on Neural Networks and Learning Systems》，《Neural Networks》，《Neural Computation》，《Journal of Multivariate Analysis》，《Engineering Applications of Artificial Intelligence》，《Cognitive Computation》，《Neurocomputing》，《中国科学》(中英文版)以及计算机领域的IJCNN，ICONIP，ICANN, ICDM等著名会议发表(含已接收)SCI、EI检索论文30余篇。
主要主持项目：
[1] 国家自然科学基金面上项目，项目编号：12271111，基于深度神经网络的复杂图数据分析算法研究，在研，主持，2023年1月-2026年12月。
[2] 广东省自然科学基金项目面上项目，项目编号：2022A1515011726，图卷积神经网络的理论研究及其应用，在研，主持，2022年1月-2024年12月。
[3] 广东省教育厅创新团队项目，项目编号：2020WCXTD011，智慧金融大数据分析团队，已结题，主持，2020年9月-2023年8月。
[4] 广东省教育厅人工智能重大领域专项，项目编号：2019KZDZX1023，基于深度学习方法的金融数据分析研究，已结题，主持，2020年3月-2022年12月。
[5] 国家自然科学基金面上项目，项目编号：11871167，面向大规模多视角数据的相关性研究及其应用，已结题，主持，2019年1月-2022年12月。
[6] 国家自然科学基金青年项目，项目编号：11401112，学习理论中的核典型相关分析及相关算法的研究和应用，已结题，主持。2015年1月-2017年12月。
[7] 国家统计局重点项目，项目编号： 2016LZ47，大数据背景下关于社交网络舆情监测的研究，3万，已结题，主持。2016年12月-2018年12月。
[8] 广州市科技计划，项目编号：201707010228，大数据背景下基于相关性分析的多媒体信息检索算法研究，20万，已结题，主持。2017年5月-2020年5月。
[9] 广东省高校自然科学研究项目，项目编号：2013LYM0032，典型相关分析和系数正则化的理论研究及其应用，3万，已结题，主持。2014年1月-2016年3月。
代表性论文：
[1] Kexin Lv, Jia Cai, Junyi Huo, Chao Shang, Xiaolin Huang* and Jie Yang*， Sparse generalized canonical correlation analysis: distributed alternating iteration based approach. Neural Computation, 2024, 36 (7): 1380-1409 (一作为博士生，中国计算机学会B类期刊)
[2] Wenwen Ye, Jia Cai, Shengping Li*. A FDA-based multi-robot cooperation algorithm for multi-target searching in unknown environments. Complex & Intelligent Systems，2024, 10, 7741-7764. (一作为博士生，中科院SCI二区)
[3] Ranhui Yan, Jia Cai*. Virtual Nodes based heterogeneous graph convolutional neural network for efficient long-range information aggregation. In Artificial Neural Networks and Machine Learning-ICANN 2024: 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17-20, 2024, Proceedings, Part V. Springer-Verlag, Berlin, Heidelberg, 217-231.
[4] Zhilong Xiong, Jia Cai*, Ranhui Yan, and Xiaolin Huang*. Noise perturbation based graph contrastive learning via flexible filters for node classification. 2024 International Joint Conference on Neural Networks (IJCNN). (EI，中国计算机学会C类会议)
[5] Jia Cai*, Tianhua Luo, Zhilong Xiong, and Yi Tang. A novel multi-level image segmentation algorithm via random opposition learning based Aquila optimizer. International Journal of Wavelets, Multiresolution and Information Processing, Volume 21, No. 06, 2023, 文章编号：2350018 (中科院SCI四区)
[6] Ranhui Yan, Jia Cai*. An end-to-end dense connected heterogeneous graph convolutional neural network. 30th International Conference on Neural Information Processing (ICONIP 2023). (通讯作者，一作为学生，中国计算机学会C类会议)
[7] Yuxiang Han, Hong Chen, Tieliang Gong, Jia Cai, Hao Den. Robust partially linear models for automatic structure discovery. Expert Systems With Applications, Volume 217, 1 May 2023, 文章编号：1195282023. (中科院SCI一区)
[8] Guanglong Xu, Zhensheng Hu, Jia Cai*. WAD-CMSN: Wasserstein distance based cross-modal semantic network for zero-shot sketch-based image retrieval. International Journal of Wavelets Multiresolution and Information Processing, Volume 21, Issue 2, 2023, 2250054. (通讯作者，一作为学生，中科院SCI四区)
[9] Zhilong Xiong, Jia Cai*. Deep heterogeneous graph neural networks via
similarity regularization loss and hierarchical fusion. Workshop of IEEE International Conference on Data Mining ( ICDM 2022 workshop). (通讯作者，一作为学生，中国计算机学会B类会议)
[10] Zhilong Xiong, Jia Cai*. Self-attention based multi-scale graph convolutional networks. 29th International Conference on Neural Information Processing (ICONIP 2022). (通讯作者，一作为学生，中国计算机学会C类会议)
[11] Jia Cai, Tianhua Luo, Guanglong Xu, Yi Tang. A novel biologically inspired approach for clustering and multi level image thresholding: modified Harris hawks optimizer. Cognitive Computation, Volume 14, Issue 3, 2022, 955-969. (中科院SCI二区)
[12] Jia Cai, Junyi Huo. Sparse generalized canonical correlation analysis via linearized Bregman method. Communications on Pure & Applied Analysis, Volume 19, Issue 8, 2020, 3933-3945.(中科院SCI三区)
[13] Jia Cai, Guanglong Xu, Zhensheng Hu. Sketch-based image retrieval via CAT loss with elastic net regularization. Mathematical Foundations of Computing, Volume 3, Issue 4, 2020, 219-227. (中科院SCI四区)
[14] Jia Cai, Guanglong Xu, Wenwen Ye. Modified grey wolf optimizer based
maximum entropy clustering algorithm. 2020 International Joint Conference on Neural Networks (IJCNN 2020). (EI，中国计算机学会C类会议)
[15] Jia Cai, Wei Dan, Xiaowei Zhang. ℓ0-based sparse canonical correlation analysis with application to cross-language document retrieval. Neurocomputing, Volume 329, 2019, 32-45. (中科院SCI二区)
[16] Jia Cai, Xiaolin Huang. Modified sparse linear discriminant analysis via
nonconvex penalties. IEEE Transactions on Neural Networks and Learning Systems, Volume 29, Issue 10 , 2018, 4957-4966. (中科院SCI一区)
[17] Jia Cai, Yi Tang. A new randomized Kaczmarz based kernel canonical correlation analysis algorithm with applications to information retrieval. Neural Networks, Volume 98, 2018, 178-191.(中科院SCI二区)
[18] Jia Cai, Hongwei Sun. Constrained ERM learning of canonical correlation
analysis: a least squares perspective. Neural Computation, Volume 29, Issue 10, 2017, 2825-2859. (中科院SCI三区)
[19] Jia Cai, Xiaolin Huang. Robust kernel canonical correlation analysis with applications to information retrieval. Engineering Applications of Artificial Intelligence, Volume 64, 2017, 33-42. (中科院SCI二区)
[20] Jia Cai, Hongwei Sun. Kernel-based conditional canonical correlation analysis via modified Tikhonov regularization. Applied and Computational Harmonic Analysis, Volume 41, 2016, 692-712. (中科院SCI一区)
[21] Jia Cai, Yi Tang, Jianjun Wang. Kernel canonical correlation analysis via
gradient descent. Neurocomputing, Volume 182, 2016, 322-331. (中科院SCI二区)
[22] Jia Cai, Daohong Xiang. Statistical consistency of coefficient-based conditional quantile regression. Journal of Multivariate Analysis, Volume 149, 2016, 1-12.(中科院SCI三区)
[23] Jia Cai. An operator approach to analysis of conditional kernel canonical
correlation. International Journal of Wavelets Multiresolution and Information
Processing, 2015,13: Article ID: 150024, 14 pages. (中科院SCI四区)
[24] Cheng Wang, Jia Cai*. Convergence analysis of coefficient-based regularization under moment incremental condition. International Journal of Wavelets, Multiresolution and Information Processing, Volume 12, Issue 1, 2014, 19 pages. (通讯作者，中科院SCI四区)
[25] 蔡佳, 王承, 无界抽样情形下不定核的系数正则化回归。中国科学A辑, 第43卷, 第6期, 2013, 613-624.
[26] Jia Cai. The distance between feature subspaces of kernel canonical correlation analysis. Mathematical and Computer Modelling, Volume 57, Issuses 3-4, 2013, 970-975. (原中科院SCI二区)
[27] Jia Cai, Hongwei Sun. Convergence rate of kernel canonical correlation
analysis. Science in China, Series A: Mathematics, Volume 54, Issue 10, 2011, 2161-2170. (中国科学 A 辑英文版)，
[28] Jia Cai, Hongyan Wang, Ding-Xuan Zhou. Gradient learning in a classification setting by gradient descent. Journal of Approximation Theory, Volume 161, 2009, 674-692.(中科院SCI三区)