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
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.
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.
© 2020 9778818威尼斯官网-威尼斯网站手机版下载 版权所有