Jingrui He to present rare categories research at DLG-AAAI’21

Jingrui He
Jingrui He, Associate Professor

Associate Professor Jingrui He will present her research at the International Workshop on Deep Learning on Graphs, which will be held in conjunction with the 35th AAAI Conference on Artificial Intelligence (AAAI'21) on February 2-9. The one-day workshop brings together academic researchers and industrial practitioners from different backgrounds to investigate new approaches and methods at the intersection of Graph Neural Networks and real-world applications.

Her talk, "Exploring Rare Categories on Graphs: Local vs. Global," will address "rare categories," or underrepresented classes in data sets where the proportion of examples belonging to different categories varies greatly.

"For example, in a data set consisting of a large number of financial transactions, only a small number of them are marked as fraudulent, and the remaining are legitimate," she said.

According to Associate Professor He, rare categories are prevalent across many high-impact applications in the security domain where the input data can be represented as graphs. Her talk will focus on two strategies for exploring rare categories—local and global.

"With the local strategy, the goal is to explore a small neighborhood around a seed node (a known example from the rare category, such as a fraudster in my previous example) to identify additional rare examples. The global strategy explores the entire graph, in order to identify rare category-oriented representations," she said.

Jingrui 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

iSchool researchers discuss misinformation

Several iSchool researchers participated in the recent Misinformation Research Symposium, which was hosted by the Center for Social and Behavioral Science and sponsored by the Center for Advanced Study, Interdisciplinary Health Sciences Institute, and National Center for Supercomputing Applications. The goals of the symposium were to help connect misinformation research on campus, foster interdisciplinary teams interested in collaborating on external submissions, and learn more about the needs of existing and emerging research groups on campus. 

Black and Knox pen chapters for new handbook on information policy

A new book on information policy includes chapters by Professor Emeritus Alistair Black and Associate Professor and Interim Associate Dean for Academic Affairs Emily Knox. Research Handbook on Information Policy, edited by Alistair S. Duff, was recently published by Edward Elgar Publishing. The handbook covers topics such as the history and future of information policy, freedom of information and expression, intellectual property, and information inequality.

research handbook on information policy

Disciplining Data: A conversation with a school of information sciences dean

Eunice Santos, professor and dean of the School of Information Sciences at the University of Illinois Urbana-Champaign, recently sat down with David B. Wilkins, faculty director of the Harvard Law School Center on the Legal Profession, for a conversation about the intersection of information sciences and the law, and how to train students to be effective collaborators and translators between the disciplines.

Eunice Santos

Maemura to join iSchool faculty

The iSchool is pleased to announce that Emily Maemura will join the faculty as an assistant professor in January 2022. She recently completed her PhD at the University of Toronto's Faculty of Information, with a dissertation exploring the practices of collecting and curating web pages and websites for future use by researchers in the social sciences and humanities.

Emily Maemura

Rolling Stone the subject of undergraduate research

BS/IS student Hanyu (Zella) Zhao learned about pop culture and data analytics through her work on the undergraduate research project, Analysis on Rolling Stone Magazine Covers. Professor Michael Twidale mentored her during the project, in which a team of undergraduates created a database of celebrities who appeared on the magazine cover from 1967 to 2021.

Zella Zhao