【个人简介】
2018年博士毕业于香港大学计算机科学系,毕业后曾任职于北京大学深圳研究生院,2022年加入广外,从事自然语言处理(如自动问答系统、词嵌入)及数据挖掘(如图嵌入、图分析)、人工智能(如联邦学习)等相关研究。在《IEEE Network》、《Information Sciences》、《Neurocomputing》、IJCAI、IJCNN等国内外期刊和会议发表学术论文十余篇(其中一作或通讯11篇),授权国家发明专利4项。主持省部级项目2项,省教育厅项目1项,市级项目1项(子课题负责人)。
社会服务方面,担任中文信息学会(CIPS)青工委委员、CCF自然语言处理委员会委员,担任ACL、TNNLS等国际顶级会议及期刊的审稿人。
【研究方向】
自然语言处理(如自动问答系统、词嵌入)、数据挖掘(如图嵌入、图分析)、人工智能安全(如联邦学习)
【学生招收】
本人有较丰富的论文指导经验,会根据学生特长定制合适的培养计划与研究方向,并对方法构思、论文写作、论文发表进行全流程的协助。
欢迎想从事自然语言处理或人工智能研究的同学们联系我(yzliang@gdufs.edu.cn、Miyayz@163.com),包括本科生与硕士生(学硕或专硕),硕士生要求具有独立完成python编程的能力。
【相关成果】
-项目
广东省自然科学基金,基于LDA的可监管推荐系统,2021.01-2023.12 (主持)
广东省自然科学基金,基于图卷积网络的可推理自动问答系统,2020.01-2022.12 (主持)
广东省教育厅特色创新(自科),基于实体关系对齐词嵌入及传播网络聚集系数分析的跨方言社交媒体不实言论检测 2023.09.21-2025.10.01 (主持)
深圳市创新创业计划-技术攻关面上项目,基于可信隔离联邦学习的跨金融业态智能引擎系统关键技术研发,2020.01-2021.12 (子课题负责人)
国家自然科学基金委员会面上项目,基于深度强化学习与时序链路预测的无线网络资源优化机制研究,2021.01-2024.12 (参与)
广东省科技厅-重点领域研发计划项目,项自主可控的联盟区块链关键技术研究,2020.08-2023.08 (参与)
-期刊论文
[1] Yiqi Deng, Yuzhi Liang*, Siu-Ming Yiu: Towards interpretable stock trend prediction through causal inference. Expert Syst. Appl. 238(Part B): 121654 (2024) (通讯作者,SCI期刊,JCR Q1, IF 7.5)
[2] Shijie Na, Yuzhi Liang*, Siu-Ming Yiu: A federated learning incentive mechanism in a non-monopoly market. Neurocomputing 586: 127630 (2024) (通讯作者,SCI期刊,JCR Q1, IF 5.779)
[3] Kai Lei, Yuzhi Liang* and Wei Li, "Congestion Control in SDN-based Network via Multi-task Deep Reinforcement Learning", IEEE Network Magazine, 34.4 (2020): 28-34 (通讯作者,SCI期刊,JCR Q1, IF 10.693)
[3] Yuzhi Liang, Chen Chen, Yukun Wang, Kai Lei*, Min Yang and Ziyu Lu. "Reachability Preserving Compression for Dynamic Graph", Information Sciences, 520 (2020): 232-249. (SCI 期刊,JCR Q1, IF 6.795)
[5] Kai Lei, Qiuai Fu, Min Yang and Yuzhi Liang*, "Tag Recommendation by Text Classification with Attention-Based Capsule Network",Neurocomputing, 391 (2020): 65-73. (通讯作者,SCI 期刊,JCR Q1, IF 5.719)
[4] Weijing Wu, Yang Deng, Yuzhi Liang* and Kai Lei, "Answer Category-Aware Answer Selection for Question Answering" , IEEE Access, vol. 9, pp. 126357-126365, 2021, (通讯作者,SCI期刊,JCR Q2, IF 3.745)
[5] Yuzhi Liang, Min Yang, Jia Zhu* and S.M. Yiu. "Out-domain Chinese new word detection with statistics-based character embedding." Natural Language Engineering, (2019): 1-17. (SCI 期刊,JCR Q2, IF 1.465)
[6] Min Yang, Yuzhi Liang, Wei Zhao, Wei Xu, Jia Zhu* and Qiang Qu. "Task-oriented keyphrase extraction from social media". Multimedia Tools and Applications, (2018) 77:3171–3187. (SCI期刊,JCR Q2, IF 2.10)
[7] Changqin Huang , Jia Zhu*, Yuzhi Liang , Min Yang ,Gabriel Pui Cheong Fung and Junyu Luo. "An efficient automatic multiple objectives optimization feature selection strategy for internet text classification". International Journal of Machine Learning and Cybernetics, 10 (2019):1151–1163. (SCI期刊,JCR Q2, IF 3.84)
[8] Yuzhi Liang*, Pengchen Yin and S. M. Yiu. "New Word Detection and Tagging on Chinese Twitter Stream". Transactions on Large-Scale Data-and Knowledge-Centered Systems, 32 (2017): 69-90. (EI 检索)
-会议论文
[1] Kai Lei, Hao Ye and Yuzhi Liang*, “Towards a Translation-Based Method for Dynamic Heterogeneous Network Embedding”, IEEE International Conference on Communications (ICC), 2021 (通讯作者,CCF C类会议)
[2] Kai Lei, Qiuai Fu and Yuzhi Liang*, "Multi-Task Learning with Capsule Networks". IJCNN 2019, Budapest, Budapest, Hungary on July 11-14, 2019 (通讯作者,CCF C)
[3] Yuzhi Liang, Jia Zhu., Yupeng Li, Min Yang and S.M. Yiu. "Relevant Fact Selection for QA via Sequence Labeling". International Conference on Knowledge Science, Engineering and Management (KSEM), 2017 (CCF C)
[4] Jia Zhu , Yuzhi Liang, Changqin Huang* , Min Yang, Jing Xiao and Yong Tang. "A Novel Approach for Adverse Events Detection". Workshop of the 26th International Joint Conference on Artificial Intelligence(IJCAI), 2017 (CCF A, workshop)
[5] Yuzhi Liang*, Pengchen Yin and S. M. Yiu. , "New Word Detection and Tagging on Chinese Twitter Stream". International Conference on Big Data Analytics and Knowledge Discovery Springer, 2015
[6] Yuzhi Liang, K. P. Chow, Lucas C. K. Hui, Junbin Fang, S.M. Yiu and Shuhui Hou. "Towards a Better Similarity Measure for Keyword Profiling via Clustering". Workshop of the 37th IEEE Computer Society International Conference on Computers (COMPSAC), 2013 (CCF C, workshop)
-专利
1. 少数类样本的生成方法、装置、计算设备及存储介质(发明专利,2020.06授权)
发明人:梁予之;杨敏;曲强
2. 基于词标签的词语标注方法,装置,服务器及存储介质(发明专利,2020.10授权)
发明人:梁予之;曲强
3. 数字货币交易中异常实体的检测方法、存储介质 (发明专利,2021.09授权)
发明人:雷凯;梁予之;吴维晶
4. 一种具有隐私保护的交通流控制方法、交通信号控制系统 (发明专利,2021.09授权)
发明人:梁予之;陈易翔;董文俊;雷凯;张良杰;何晟;闽松江