Seminar on Advanced Operators for Graph Neural Networks : vTools Events

IEEE.org | IEEE Xplore Digital Library | IEEE Standards | IEEE Spectrum | More Sites

Seminar on Advanced Operators for Graph Neural Networks

#Graph #Neural #Networks

Advanced Operators for Graph Neural Networks

Dr. Yao Ma

Department of Computer Science

New Jersey Institute of Technology

Time: 9pm-10pm, Tue., October 12, 2021

Place: Virtual meeting, Newark, NJIT

Abstract:

Graph structured data are ubiquitous in the real world such as social networks, molecular graphs, and emerging among a plethora of other diverse domains. Therefore, it is of great research importance to design advanced algorithms for representation learning on graph-structured data to facilitate improved predictions across numerous computational methods. Graph Neural Networks (GNNs), which generalize the deep neural network models to graph-structured data, pave a new way to effectively learn representations at both the graph and individual node levels. We have significantly contributed to the fundamental research of GNNs by developing novel algorithms and practical research of GNNs by investigating their safety issues and real-world applications. This talk presents two fundamental about key operations of GNNs, i.e., graph filtering operation and graph pooling operation. It first presents some commonly used graph filtering operations and then demonstrates how they can be observed from a unified graph signal denoising perspective. This talk also introduces a graph pooling operation based on spectral graph theory, which helps GNNs learn better graph-level representations.

Bio:

Yao Ma is an assistant professor in Department of Computer Science at New Jersey Institute of Technology (NJIT). He received his Ph.D. in Computer Science from Michigan State University (MSU) in 2021. His major research interest lies in Graph Neural Networks (GNNs) for representation learning on graph-structured data. He has significantly contributed to the fundamental research and practical research of GNNs, which leads to numerous innovative work in top-tier conferences such as KDD, WWW, SIGIR, WSDM, ICDM, and ICML. He was the leading organizer and presenter of two well-received tutorials on GNNs at AAAI'2020, AAAI’2021, KDD’2020, and KDD'2021, attracting more than 1000 attendees in total. His recent book Deep Learning on Graphs has attracted tens of thousands of downloads from more than 100 countries. He received the Outstanding Graduate Student Award (2019-2020) from the College of Engineering at MSU.