Headline:Representation Learning on Network，Deep Learning and Marine New Energy Application
Time: 9:00 am, on May 13th, 2019
Venue:Academic Report Hall in Annex Building of B8, Southern Campus of SCUT
Networks are ubiquitous and are a part of our common vocabulary. Network science and engineering has emerged as a formal field over the last twenty years and has seen explosive growth. Ideas from network science are central to companies such as Akamai, Twitter, Google, Facebook, and LinkedIn. The concepts have also been used to address fundamental problems in diverse fields (e.g., biology, economics, social sciences, psychology, power systems, telecommunications, public health and marketing). Researchers in network science have traditionally relied on user-defined heuristics to extract features from complex networks (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode network structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. These network representation learning (NRL) approaches remove the need for painstaking feature engineering and have led to state-of-the-art results in network-based tasks, such as node classification, node clustering, and link prediction. In this talk, we will cover key advancements in NRL with an emphasis on fundamental advancements made in the last several years. We will discuss classic matrix factorization-based methods and recently development random-walk based algorithms (e.g., DeepWalk and node2vec). We will also introduce our proposed approaches, such as multi-label network representation learning and topical network embedding, as well as very recent advancements in graph neural networks. Finally, we will introduce our recent work on deep learning applications in marine renewable energy generation system prognostic health management.
Yufei Tang is an Assistant Professor in the Department of Computer & Electrical Engineering and Computer Science (CEECS) at Florida Atlantic University (FAU). He is also the Director of the Intelligent and Resilient Systems (IRS) Research Group. He received his Ph.D. in Electrical Engineering from the University of Rhode Island (URI) in 2016. His research interests are in the areas of Computational Intelligence (e.g., Machine Learning, Networked Big Data Mining) and Cyber-Physical Systems (e.g., Ocean Energy Systems, Smart Grid). Dr. Tang is currently collaborating with the Southeast National Marine Renewable Energy Center (SNMREC), the National Renewable Energy Laboratory (NREL) and researchers/labs from many other universities. Dr. Tang is the reviewer for many top-tier journals and conferences, such as the IEEE Transactions on Neural Network and Learning Systems (TNNLS), IEEE Transactions on Smart Grid (TSG), IEEE Transactions on Power Systems (TPS), IEEE Transactions on Big Data (TBD), IEEE International Conference on Data Mining (ICDM), and AAAI Conference on Artificial Intelligence.