头像

姓名:张静

职称:教授

电话:

办公室:李文正楼北435

个人主页:

邮箱:jingz@seu.edu.cn

教育背景

学术兼职

IEEE高级会员(Senior Member,Since 2019)

- 常年担任AAAI、IJCAI、KDD、ICML、NeurIPS、ICLR、ICDM、WSDM、SDM、CIKM、ECAI等人工智能相关领域顶级和权威国际会议程序委员会成员(PC/SPC Member)


研究领域

安全可信人工智能

数据挖掘与机器学习

大数据与内容安全

研究概况

主要研究方向为安全可信人工智能及应用,包括但不限于:

  • 可信人工智能(噪声鲁棒性学习、不平衡学习、小样本学习等特定场景下的学习方法)

  • 人工智能安全(样本对抗攻防、数据投毒攻防、后门攻击与防御)

  • 人在回路(Human-In-the-Loop)机器学习(众包学习、主动学习、可靠激励机制)

  • 联邦学习与图表示学习及其安全机制

  • 隐私保护的学习(联邦学习、迁移学习、知识蒸馏)

  • 大模型与内容安全(大模型精调、提示工程、知识图谱与大模型融合、AIGC内容检测)

  • 应用领域:可信AI+(医疗、金融、网络安全、软件工程、工业互联网等)


最近动态

研究课题

2024 企业横向委托课题A,主持,在研(2024.01-2024.12)

2022 中央高校基本科研业务费(东南大学科研启动经费),主持,在研(2023.01-2025.12)

2021 之江实验室开放课题项目,2019KD0AD01/015,交互式众包标注主动学习方法研究,主持,已结题(2022.02-2023.02)

2020 国家自然科学基金,面上项目,62076130,面向众包标注数据的机器学习方法研究,主持,在研(2021.01-2024.12)

2019 国家重点研发计划,科技创新2030-“新一代人工智能”重大项目,2018AAA0102002,分布式跨媒体知识获取与管理,子课题负责人,已结题(2019.12-2023.12)

2018 国家自然科学基金,重大研究计划(大数据驱动的管理与决策研究)培育项目,91846104,众包大数据多源异构融合与知识学习,主持,已结题(2019.01-2021.12)

2016 国家自然科学基金,青年科学基金,61603186,面向众包标注的真值推断与监督分类关键问题研究,主持,已结题(2017.01-2019.12)

2017 中国博士后科学基金,特别资助项目,2017T100370,融合样本特征的众包标注数据学习方法研究,主持,已结题(2017.01-2018.12)

2016 中国博士后科学基金,面上项目(一等),2016M590457,面向图像分类众包标注的监督学习方法研究,主持,已结题(2016.01-2017.12)

2016 苏省自然科学基金青年项目,BK20160843,面向众包标注的主动学习方法研究,主持,已结题(2016.07-2019.06)

2016 江苏省博士基金C类资助,1601199C,主持,已结题(2016.01-2017.12)

2016 江苏省社会公共安全图像与视频理解重点实验室开放课题,30916014107,主持,已结题(2016.07-2018.06)

2015 中央高校基本科研业务费,主持,已结题(2015.07-2017.06)


奖励与荣誉

课程信息

《数据结构基础》(本科生 64课时)


学术成果

发表各类期刊和会议论文100余篇,授权发明专利4项,登记软件著作权3项。

【代表性期刊论文,*通讯作者】  

[18] Xiaoqian Jiang, Jing Zhang, Ming Wu, & Cangqi Zhou. (2024). TiFedCrowd: Federated Crowdsourcing with Time-Controlled Incentive. IEEE Transactions on Emerging Topics in Computational Intelligence.

[17] Jing Zhang, Ming Wu, Zeyi Sun, & Cangqi Zhou. (2024). Learning from crowds using graph neural networks with attention mechanism. IEEE Transactions on Big Data.

[16] Cangqi Zhou, Hui Chen, Jing Zhang*, Qianmu Li, & Dianming Hu. (2024). Quintuple-based representation learning for bipartite heterogeneous networks. ACM Transactions on Intelligent Systems and Technology.

[15] Zijian Ying, Jing Zhang*, Qianmu Li, Ming Wu, & Victor S. Sheng. (2023). A little truth injection but a big reward: Label aggregation with graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14] Jing Zhang, Yu Lei, Yuxiang Wang, Cangqi Zhou, & Victor S. Sheng. (2023). Hierarchical graph capsule networks for molecular function classification with disentangled representations. IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[13] Jing Zhang, Ming Wu, Cangqi Zhou, & Victor S. Sheng. (Mar. 2024). Active Crowdsourcing for Multilabel Annotation. IEEE Transactions on Neural Networks and Learning Systems, 35(3): 3549–3559.

[12] Jing Zhang, Sunyue Xu, & Victor S. Sheng. (Aug. 2023). CrowdMeta: Crowdsourcing truth inference with meta-knowledge transfer. Pattern Recognition, 140: 109525

[11] Jing Zhang. (2022). Knowledge learning with crowdsourcing: A brief review and systematic perspective. IEEE/CAA Journal of Automatica Sinica, 9(5): 749–762. 

[10] Jing Zhang & Xindong Wu. (2021). Multi-label truth inference for crowdsourcing using mixture models. IEEE Transactions on Knowledge and Data Engineering. 33(5): 2083–2095.

[ 9 ] Jing Zhang, Mengxi Li, Kaisheng Gao, Shunmei Meng, & Cangqi Zhou. (2021). Word and graph attention networks for semi-supervised classification. Knowledge and Information Systems, 63: 2841–2859.

[ 8 ] Jing Zhang, Victor S. Sheng, & Jian Wu. (2019). Crowdsourced label aggregation using bilayer collaborative clustering. IEEE Transactions on Neural Networks and Learning Systems, 30(10): 3172–3185.

[ 7 ] Jing Zhang, Ming Wu, & Victor S. Sheng (2019). Ensemble learning from crowds. IEEE Transactions on Knowledge and Data Engineering, 31(8): 1506–1519.

[ 6 ] Victor S. Sheng, Jing Zhang*, Bin Gu*, & Xindong Wu. (2019). Majority voting and pairing with multiple noisy labeling. IEEE Transactions on Knowledge and Data Engineering, 31(7): 1355–1368.

[ 5 ] Jing Zhang, Victor S. Sheng, Tao Li, & Xindong Wu. (2018). Improving crowdsourced label quality using noise correction. IEEE Transactions on Neural Networks and Learning Systems, 29(5): 1675–1688.

[ 4 ] Jing Zhang, Victor S. Sheng, Jian Wu, & Xindong Wu. (2016). Multi-class ground truth inference in crowdsourcing with clustering. IEEE Transactions on Knowledge and Data Engineering, 28(4): 1080–1085.

[ 3 ] Jing Zhang, Xindong Wu, & Victor S. Sheng. (2015). Active learning with imbalanced multiple noisy labeling. IEEE Transactions on Cybernetics, 45(5): 1081–1093.

[ 2 ] Jing Zhang, Xindong Wu, & Victor S. Sheng. (2015). Imbalanced multiple noisy labeling. IEEE Transactions on Knowledge and Data Engineering, 27(2): 489–503.

[ 1 ] Jing Zhang, Victor S. Sheng, Bryce A. Nicholson, & Xindong Wu. (2015). CEKA: A tool for mining the wisdom of crowds. Journal of Machine Learning Research, 16: 2853–2858.

【代表性会议论文,*通讯作者】

[13] Xiaoqian Jiang, Haiyang Diao, Cangqi Zhou, & Jing Zhang*. (2024). Timeliness-Selective Incentive Federated Crowdsourcing. In 2024 IEEE International Conference on Web Service (ICWS-2024) , Shenzhen, China.

[12] Cangqi Zhou, Yuxiang Wang, Jing Zhang*, Jiqiong Jiang, & Dianming Hu. (2022). End-to-end modularity-based community co-partition in bipartite networks. In Proceedings of 31th ACM International Conference on Information and Knowledge Management (CIKM-2022), Atlanta, GA, USA.

[11] Cangqi Zhou, Hui Chen, Jing Zhang*, Qianmu Li, & Dianming Hu. (2022). AngHNE: Representation learning for bipartite heterogeneous networks with angular loss. In Proceedings of the 15th International Conference on Web Search and Data Mining (WSDM-2022), Phoenix, Arizona, USA. 

[10] Cangqi Zhou, Jinling Shang, Jing Zhang*, Qianmu Li, & Dianming Hu. (2021). Topic-attentive encoder-decoder with pre-trained language model for keyphrase generation. In Proceedings of the 21st International Conference on Data Mining (ICDM-2021), Auckland, New Zealand.

[ 9 ] Yu Lei & Jing Zhang*. (2021). Capsule graph neural networks with EM routing. In Proceedings of 30th ACM International Conference on Information and Knowledge Management (CIKM-2021), Gold Coast, Queensland, Australia. 

[ 8 ] Jing Zhang, Huihui Wang, Shunmei Meng, & Victor S. Sheng. (2020). Interactive learning with proactive cognitive enhancement for crowd workers. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-2020), New York, USA.

[ 7 ] Yanhui Peng & Jing Zhang*. (2020). LineaRE: Simple but powerful knowledge graph embedding for link prediction. In Proceedings of 20th IEEE International Conference on Data Mining (ICDM-2020), Sorrento, Italy.

[ 6 ] Victor S. Sheng & Jing Zhang*. (2019). Machine learning with crowdsourcing: A brief summary of the past research and future directions. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI-2019), Honolulu, Hawaii, USA.

[ 5 ] Huihui Wang, Shunmei Meng, Jinbiao Yu, & Jing Zhang*. (2019). Fast classification algorithms via distributed accelerated alternating direction method of multipliers. In Proceedings of the 2019 International Conference on Data Mining (ICDM-2019), Beijing, China. 

[ 4 ] Jing Zhang & Xindong Wu. (2018). Multi-label inference for crowdsourcing. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2018), London, UK.

[ 3 ] Jing Zhang, Victor S. Sheng, & Tao Li. (2017). Label aggregation for crowdsourcing with bi-layer clustering. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-2017), Tokyo, Japan.

[ 2 ] Jing Zhang, Victor S. Sheng, Jian Wu, Xiaoqin Fu, & Xindong Wu. (2015). Improving label quality in crowdsourcing using noise correction. In Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM-2015), Melbourne, Australia.

[ 1 ] Jing Zhang, Xindong Wu, & Victor S. Sheng. (2013). Imbalanced multiple noisy labeling for supervised learning. In Proceedings of the 27th AAAI Conference on Artificial Intelligence (AAAI-2013), Bellevue, Washington, USA.

【授权发明专利】

[ 3 ] 第一发明人. 基于标注者可靠度时序建模的众包主动学习方法和装置. 202210512110.0

[ 2 ] 第一发明人. 医疗咨询信息聚合分析方法. 201811211126.8.

[ 1 ] 第一发明人. 一种分布式MRCP服务器负载均衡系统的均衡方法. 200910185900.7.


其他