He receives grant to improve performance of deep learning models

Jingrui He
Jingrui He, Associate Professor and MSIM Program Director

Associate Professor Jingrui He has been awarded a two-year, $149,921 grant from the National Science Foundation (NSF) to improve the performance of deep learning models. For her project, "Weakly Supervised Graph Neural Networks," she will focus on the lack of labeled data in Graph Neural Networks (GNNs), a deep learning method designed to perform inference on data described by graphs.

A graph is a structured way to represent data, with nodes representing entities and edges representing the relationships between these entities. GNNs provide an easy way to conduct node-level, edge-level, and graph-level prediction via machine learning. However, they usually require a large amount of label information to train the model parameters. According to He, the lack of labeled data in graphs can render many existing deep learning models ineffective in achieving the desired performance. Her new project involves a work-around so that GNNs can use unlabeled data and other relevant information.

"For example, in fraud detection, the number of known fraudulent transactions is usually very small compared to the total number of transactions, hence the lack of labeled data. Most existing GNN models tend to suffer from such label scarcity. In my new project, we aim to address this issue by leveraging weak supervision or additional information (besides the limited label information), such as labeled data from other related applications and/or access to a domain expert, in order to compensate for the lack of labeled data," said He.

In addition to fraud detection, areas such as agriculture and cancer diagnosis could also benefit from this research. He’s project will lead to a suite of new models, algorithms, and theories for constructing high-performing GNNs with weak supervision, and for understanding the benefits of weak supervision with respect to the model generalization performance and sample complexity.

He's general research theme is to design, build, and test a suite of automated and semi-automated methods to explore, understand, characterize, and predict real-world data by means of statistical machine learning. She received her PhD in machine learning from Carnegie Mellon University.

Updated on
Backto the news archive

Related News

Spectrum Scholar Spotlight: Wardah Mohammed

MSLIS student and ALA Spectrum Scholar Wardah Mohammed earned her bachelor's degree in philosophy with a focus in bioethics, global studies, and Arabic language and culture from Loyola University Chicago.

Wardah Mohammed

Site of integrated Illinois town founded by former slave is newest national park

The New Philadelphia National Historic Site in western Illinois, commemorating the first U.S. town to be legally founded by African Americans, is the nation's newest national park. The national park designation in late December is the result of years of work by descendants of New Philadelphia's inhabitants, Pike County residents living near the former village, University of Illinois Urbana-Champaign professors and students, and collaborators from across the nation.

aerial view of New Philadelphia

Benson to share copyright expertise in new roles

Sara Benson (MSLIS '17), adjunct associate professor at the iSchool and copyright librarian and associate professor at the University Library, was recently named a senior policy fellow for the American Library Association's Public Policy and Advocacy Office and the International Federation of Library Associations and Institutions (IFLA) representative to the World Intellectual Property Organization (WIPO) Standing Committee on Copyright and Related Rights (SCCR). 

Sara Benson

New book exploring provenance authored by iSchool PhD student, alumni

Documenting the Future: Navigating Provenance Metadata Standards, a new book authored by PhD student Michael Gryk and alumni Rhiannon Bettivia (PhD '16) and Jessica Yi-Yun Cheng (PhD '22), explores provenance, which is the study and documentation of how something has come to be. Provenance documentation is critical for authenticity, trustworthiness, and reproducibility in science. 

Michael Gryk

Project to study anti-Black violence in newspapers receives support from Mellon Foundation

A project to examine the circulation of newspaper reports about anti-Black violence in nineteenth- and early twentieth-century U.S. newspapers could provide context to the spread of white supremacist ideologies in social media today. "The Virality of Racial Terror in US Newspapers, 1863-1921" (VRT) is a partnership between the University of Illinois Urbana-Champaign, Northeastern University, and Washington University, with Illinois serving as the lead institution. VRT was recently awarded a $500,000 grant from the Mellon Foundation, as part of its Higher Learning program that supports inquiry into issues of vital social, cultural, and historical import.

St. Louis newspaper from early 1900s