9778818威尼斯官网-威尼斯网站手机版下载

当前位置: 首页 >> 科学研究 >> 学术讲座 >> 正文
【海韵讲座】2020年第6期-Graph Neural Networks and its Application in Multivariate Time Series Forecasting
发布时间:2020年10月15日 浏览次数:

报告题目:Graph Neural Networks and its Application in Multivariate Time Series Forecasting

主讲人:吴宗翰, 悉尼科技大学 博士生

时间:20201030日(星期五)15:00-16:00

地点:海韵园行政楼C505会议室

摘要:

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this talk, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into different categories. With a focus on graph convolutional networks, we review alternative architectures that have recently been developed; these learning paradigms include graph attention networks, graph autoencoders, graph generative networks, and graph spatial-temporal networks. We further discuss the applications of graph neural networks across various domains, in particular, multivariate time series forecasting.

报告人简介:

Zonghan Wu is a 3rd year Ph.D. student in University of Technology Sydney. His research focuses on graph neural networks. He has published papers in top-tier conferences (IJCAI-2019, KDD-2020) and journals (IEEE TNNLS). His recent survey paper on GNN has reached 800+ citations.

邀请人:计算机系 范晓亮高级工程师

Top