REU Site: Multidisciplinary Graph Data Analytics

Georgia State University Research Foundation, Inc., Atlanta GA

Investigators

Abstract

The Research Experience for Undergraduates (REU) site: Multidisciplinary Graph Data Analytics at Georgia State University is an eight-week summer research program to provide undergraduates a research-intensive training and offer valuable opportunities to actively engage in multidisciplinary data analytics projects. This award will recruit ten undergraduate students each summer from colleges with limited research capabilities and high concentrations of underrepresented minority populations such as African Americans and Hispanics in Georgia and neighboring states. The goals of the project include (1) providing a quality research experience for undergraduates, (2) increasing participation of female and under-represented minorities in data analytics (particularly graph data analytics), which will contribute to the broadening of diversity in computing fields, and (3) preparing students to pursue graduate studies and professional careers in research-oriented positions. The participants will engage in research projects in graph data analytics with practical applications in social networks, bioinformatics, and business analytics under faculty mentors' mentorship and guidance. Additionally, students will gain insights into industry research practices through field trips and guest speaker sessions. Upon completion of the program, participants are expected to acquire a robust skill set essential for successful careers in science and technology, particularly in the ever-growing field of data science—an area projected to remain pivotal in the future professional landscape. This REU site aims to engage undergraduates in learning experiences that increase their interest and ability to conduct basic research, especially on graph data analytics. Students will learn how to develop and use different graph machine learning (e.g., graph neural networks), graph data mining (e.g., graph clustering), and statistical methods (e.g., regression) while working on real-world projects with applications in social networks, bioinformatics, and business analytics. The research projects will fall into the following categories: 1) Graph Neural Networks with Graph Compressing, 2) Influence Maximization on Business Networks, 3) Social Network Analysis using Knowledge Graphs, and 4) Biomedical Data Analysis using Heterogeneous Graphs. Students will further learn about the ethical challenges inherent in data analytics, from privacy issues to problems emerging from machine learning applied to biased datasets via weekly seminars. Through regular meetings, where diverse problems and experiences are shared and knowledge is exchanged, students will not only delve into their projects but also gain exposure to other ongoing projects. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.