Georgia State University’s Assistant professor in Department of Computer Science and TCV Faculty, Dr. Esra Akbas has been awarded a new grant from the National Science Foundation (NSF). The new grant is estimated at $500,00 from The Faculty Early Career Development (CAREER) Program, which awards in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. Akbas, as PI will use this funding to continue her research on graph machine learning and its application to drug repurposing and event detection problems with collaborating experts from different domains. One specific application she will work on is analyzing dynamic extremist group networks via GNN to understand their structure and detect their events. The project’s duration is expected to last from August 2024 to August 2029.
Abstract
Many real-world domains can be represented as graphs. For instance, a roadmap can be represented as a graph where cities are the nodes and roads connecting cities are the edges connecting the nodes. Graph Neural Network (GNN), a deep learning model that operates on graph-structured data, facilitates solutions for various graph analytic tasks and crucial real-world problems. Despite the popularity and success of GNN, the size and complexity of real-world networks, such as their diverse connectivity patterns, and dynamic nature, have imposed significant issues including oversmoothing, structural loss, and redundancy. The goal of this CAREER proposal is to develop novel GNN models via incorporating graph compression methodologies that create a smaller compressed graph preserving the desired structural information of large graphs specific to the selected problems to address the issues of GNN. Developed models will be utilized for many real-world applications in biomedical, social, and security fields. Compressing graphs will also achieve several benefits, including significant time and memory space reduction, and improved data privacy. Additionally, the investigator will integrate research with education by organizing several activities including outreach to high school and UG students, underrepresented groups, and HBCUs to attract women and minorities to the computing field.
Dr. Akbas leads the Data Engineering Lab (DELab) at GSU with a team of PhD, MS, and UG students. In DELab, they work on problems ranging from the algorithmic side of machine learning to applications in real-world problems. Their focus is graph mining, graph machine learning, network science, and social network analysis and their applications in social, biological, and medical domains. She also has received NSF CRII and NSF REU Site funding. With her NSF REU Site funding on Multidisciplinary Graph Data Analytics, she organize 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.
https://sites.google.com/view/esraakbas/
For Transcultural Conflict and Violence at GSU
Press Inquiries Contact
J. Dante McBride,
Public Relations
404-413-5676
[email protected]