[2022-May-18] Graph Machine Learning and Its Applications

Institute of Information Systems and Applications

Speaker:

 

Prof. Cheng-Te Li 李政德副教授

National Cheng Kung University 國立成功大學

Topic:

Graph Machine Learning and Its Applications

Date:

13:20-15:00 Wednesday 18-May-2022

QR Code:

Link:

https://meet.google.com/zry-pxjc-htx

Hosted by:

Prof. Chun-Yi Lee

Abstract

Graphs depict how entities connect and interact with one another, and enable fundamental predictive tasks, including node classification (NC) and link prediction (LP). With the blooming and advances of deep learning, novel Graph Representation Learning (GRL) and Graph Neural Networks (GNN) models, which learn the representations of nodes and graphs, are invented and widely applied on social and information networks. How can GRL/GNN be applied for data science? In this talk, I will utilize our recent research outcomes to exhibit what, where, and how graph machine learning can benefit a variety of tasks in data science. First, I will first give a review on both unsupervised and supervised GRL for typical NC and LP tasks. Second, I will show that GRL can be applied to better model and exploit diverse relationships between various types of nodes in the realms of recommender systems and knowledge base. Third, through the applications to fake news detection, air quality forecasting, traffic flow forecasting, customs fraud detection, and stock price prediction, I will further exhibit that GRL and GNN are powerful even when the graphs cannot be observed.

Bio.

Dr. Cheng-Te Li is now an Associate Professor at Institute of Data Science, National Cheng Kung University (NCKU), Tainan, Taiwan. He received his Ph.D. degree (2013) from Graduate Institute of Networking and Multimedia, National Taiwan University. Before joining NCKU, he was an Assistant Research Fellow (2014-2016) at CITI, Academia Sinica. Dr. Li’s research targets at Machine Learning and Data Mining with their applications to Social Networks, and Social Media, Recommender Systems, and Natural Language Processing. His work has been published at premier conferences, including KDD, TheWebConf (WWW), ICDM, CIKM, SIGIR, IJCAI, ACL, EMNLP and NAACL. Dr. Lis academic recognition includes: 傑出人才發展基金會年輕學者創新獎 (2021), 科技部未來科技獎 (2021, 2020), 成大管理學院研究傑出獎 (2021, 2020), TAAI 2020最佳論文獎, 李國鼎青年研究獎 (2019), 科技部哥倫布計畫 (2018), and 潘文淵基金會考察研究獎 (2016). He leads Networked Artificial Intelligence Laboratory (NetAI Lab) at NCKU.

All faculty and students are welcome to join.