He receives grant to improve performance of deep learning models

Jingrui He
Jingrui He, Associate Professor

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

CCB to host events centered on Asian American history

In 2022, Illinois became the first state in the nation to mandate the teaching of Asian American community history in public elementary and secondary high schools. The Teaching Equitable Asian American Community History (TEAACH) Act ensures that every K-12 student in Illinois learns about the contributions of Asian Americans to the economic, cultural, social, and political development of the United States. To mark the implementation of this act, the Center for Children's Books (CCB) is hosting a series of events for the 2022-2023 academic year.

Spectrum Scholar Spotlight: Inbar Michael

Thirteen iSchool master's students were named 2022-2023 Spectrum Scholars by the American Library Association (ALA) Office for Diversity, Literacy, and Outreach Services. This "Spectrum Scholar Spotlight" series highlights the School’s scholars. MS/LIS student Inbar Michael earned her bachelor's degree in history with a minor in humanities and law from the University of California, Irvine.

Inbar Michael

NSF FABRIC project completes phase 1, enabling early testing of unprecedented large-scale network experiments

The NSF-funded FABRIC project has made steady progress establishing the groundbreaking network testbed infrastructure to reimagine the way large amounts of data are generated, stored, analyzed, and transmitted across the world. With the required hardware, software, storage, and fiber optic connections in place, the FABRIC system is available for early users to build and test novel large-scale experiments. 

Anita Nikolich

Knox to co-lead new project addressing racism and social injustice

A project co-led by Emily Knox is one of the twenty-five projects that recently received funding through the Chancellor's Call to Action Research Program to Address Racism and Social Injustice. The program is a $2 million annual commitment by the University of Illinois to respond to the critical need for universities across the nation to prioritize research focused on systemic racial inequities and injustices that exist not only in communities but in higher education itself. For 2022, the funded projects will focus on systemic racism and social justice, law enforcement and criminal justice reform, and disparities in health and health care.

Emily Knox

iSchool instructors ranked as excellent

Forty-four iSchool instructors were named in the University's List of Teachers Ranked as Excellent for Spring 2022. The rankings are released every semester, and results are based on the Instructor and Course Evaluation System (ICES) questionnaire forms maintained by Measurement and Evaluation in the Center for Innovation in Teaching and Learning. Only those instructors who gave out ICES forms during the semester and who released their data for publication are included in the list.

iSchool Building