2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT 2024)



Prof. Yan Yang

Southwest Jiaotong University, China

Bio: Yan Yang received her B.Sc. and M.Sc. degree from the Huazhong University of Science and Technology in 1984 and 1987 respectively. She received her PhD degree in Traffic Information Engineering and Control in 2007 from Southwest Jiaotong University. In 2002/2003 and 2004/2005 she worked as a visiting scholar at the Center of Pattern Analysis and Machine Intelligence (CPAMI) in Waterloo University, Canada. She was also a visiting professor at the University of Illinois at Chicago, USA in 2018. She is currently Professor, Deputy Dean of School of Computing and Artificial Intelligence and holds an Academic and Technical Leader of Sichuan Province.

Prof. Yang has participated in more than 10 high-level projects recently. And has taken charge of three programs supported by the National Natural Science Foundation of China (NSFC), one Project of National Science and Technology Support Program, etc. She has authored and co-authored over 230 papers (e.g., IEEE Transaction on Knowledge and Data Engineering, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Cybernetics, IEEE Transactions on Cloud Computing) in journals and international conferences (e.g., IJCAI, ICDM, EMNLP). 1 special issue of international journal, 1 proceeding, and obtaining several authorized Chinese invention patents. She has served as conference chair, program chair, or organizing chair of many international conferences, and serves as an associate editor of International Journal of Big Data Mining and Analytics. She was a meeting review expert of the National Natural Science Award, Science and Technology Progress Award and Technology Invention Award. She won the special award of Zhan Tianyou Railway Science and Technology Award, and first prize of computer science and technology of Sichuan Province.

Prof. Yang has successively lectured undergraduate or postgraduate courses such as data structure, operating system, analysis and design of operating system, introduction to the forefront of computer science, pattern recognition, artificial intelligence and machine learning, and advanced artificial intelligence. She is responsible for national first-class undergraduate major "computer science and technology", Sichuan Excellent Courses "operating system", and Sichuan Provincial Curriculum Ideological and Political Demonstration Course. She has presided over more than 10 provincial and university-level educational reform projects, published more than 20 educational reform papers, and edited 2 textbooks. She served as an engineering education professional certification expert of the Ministry of Education and a member of the Sichuan Computer Professional Teaching Steering Committee. She presided and won the second prize of Sichuan Higher Education Teaching Achievements and the first prize of university-level teaching achievements.

Prof. Yang is a distinguished member of CCF, a senior member of CAAI, a member of IEEE, ACM, CCF Artificial Intelligence and Pattern Recognition, CCF Theoretical Computer Science, CCF Task Force on Big Data, CAAI Machine Learning, CAAI Grain Calculation and Knowledge Discovery Committee, Vice Chair of ACM Chengdu Chapter, Director of ACM SIGCSE China Chapter, Vice president of Sichuan Computer Society, and Director of Sichuan Artificial Intelligence Society.


Prof. Feihu Huang

Nanjing University of Aeronautics and Astronautics, China


Feihu Huang is a professor at the College of Computer Science and Technology/ College of Artificial Intelligence/ College of Software, Nanjing University of Aeronautics and Astronautics. He received his PhD in Engineering from Nanjing University of Aeronautics and Astronautics in December 2017. From September 2018 to July 2022, he worked at the University of Pittsburgh as a postdoctoral researcher. Selected into the National Youth Talent Program in 2022. In recent years, he has mainly focused on research on machine learning and efficient optimization. More than 30 papers have been published in important international journals and conferences on artificial intelligence and machine learning, including JMLR, TPAMI, ICML, NeurIPS, ICLR, AAAI, IJCAI, AISTATS, etc. He has served as a (senior) program committee member for important international conferences on artificial intelligence, machine learning, data mining and computer vision: ICML, NeurIPS, AAAI, IJCAI, KDD, CVPR, ICCV, ICLR, AISTATS, etc., and has also served as a member of important international journals Reviewer of JMLR, IEEE TPAMI, ML, IEEE TIP, SIAM Journal on Optimization, etc. Currently, he is hosting two NSFC projects.

Title:Efficient Adaptive Federated Minimax Optimization 

Abstract:Federated learning is a popular distributed and privacy-preserving learning paradigm in machine learning. Recently, some federated learning algorithms have been proposed to solve the distributed minimax problems. However, these federated minimax algorithms still suffer from high gradient or communication complexity. Meanwhile, few algorithm focuses on using adaptive learning rate to accelerate these algorithms. In this talk, I will report that we have proposed an efficient adaptive federated minimax optimization algorithm (i.e., AdaFGDA) to solve the nonconvex distributed minimax problems. Specifically, our AdaFGDA builds on the momentum-based variance reduced and local-SGD techniques, and it can flexibly incorporate various adaptive learning rates by using the unified adaptive matrices. Theoretically, we provide a solid convergence analysis framework for our AdaFGDA algorithm under non-i.i.d. setting. Moreover, we prove our AdaFGDA algorithm obtains a lower gradient complexity with lower communication complexity in finding stationary solutions of the nonconvex minimax problems. Experimentally, we conduct some experiments on the deep AUC maximization and robust neural network training tasks to verify efficiency of our algorithms.


Prof. Xiaofang Yuan

Hunan University, China


Xiaofang Yuan, PhD, Professor in Hunan University, doctoral supervisor. He is mainly engaged in electric vehicles, intelligent transportation, automation & control and other aspects of research work. He has presided over more than 10 projects, including National Key R&D Program of China, project of National Natural Science Foundation of China, Science and Technology Plan of Hunan Province, etc. He has more than 50 papers have been published in IEEE Transactions and other international authoritative journals in the field of electric vehicles, intelligent transportation, including 40 SCI papers.


Prof. Yunquan Dong

Nanjing University of Information Science and Technology, China


Yunquan Dong received the B.S. degree in electronic and information engineering from Qingdao University in 2005, the M.S. degree in communication and information systems from Beijing University of Posts and Telecommunications 2008, and the Ph.D. degree in communication and information engineering from Tsinghua University, Beijing, in 2014. He was a BK Assistant Professor with the Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea, from 2015 to 2016. He is currently a Professor with the School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China. His research interests include the performance evaluations and performance optimizations of wireless networks, with recent focus on age of information and ubiquitous sensing.


Prof. Wanyang Dai

Nanjing University, China


Wanyang Dai is a Distinguished Professor in Nanjing University, Chief Scientist in Su Xia Control Technology. He is the President & CEO of U.S. based (Blockchain & Quantum-Computing) SIR Forum, President of Jiangsu Probability & Statistical Society, Chairman of Jiangsu BigData-Blockchain and Smart Information Special Committee. He received his Ph.D. in mathematics and systems & industrial engineering from Georgia Institute of Technology in USA. He was an MTS and principal investigator in U.S. based AT&T Bell Labs (currently Nokia Bell Labs) with some project won “Technology Transfer” now called cloud system. He was the Chief Scientist in DepthsData Digital Economic Research Institute. He published numerous influential papers in big name journals including Probability in the Engineering and Informational Sciences, Quantum Information Processing, Operations Research, Operational Research, Queueing Systems, Computers & Mathematics with Applications, Communications in Mathematical Sciences, and Journal of Computational and Applied Mathematics. He received various academic awards and has presented over 60 keynote/plenary speeches in IEEE/ACM, big data and cloud computing, quantum computing and communication technology, computational and applied mathematics, biomedical engineering, mathematics & statistics, and other international conferences. He has been serving as IEEE/ACM conference chairs, editors-in-chief and editorial board members for various international journals ranging from artificial intelligence, machine learning, data science, wireless communication, pure mathematics & statistics to their applications.