Jundong Li

Introducing an innovative method for generating diverse and realistic graphs.

Addressing reliability, generalizability, and confidentiality in Graph ML.

FastGAS improves efficiency in selecting examples for in-context learning using a graph-based approach.

A look into Energy-Based World Models and their potential to enhance AI reasoning.

SAFER improves predictions in knowledge graphs with limited examples.

Establishing a benchmark to evaluate fairness in graph learning methods.

New framework allows for efficient removal of sensitive data from Graph Neural Networks.

This paper examines the effectiveness of current machine unlearning verification methods.

Exploring certified unlearning and its role in data privacy protection.

A new method uses shapes to improve how computers recognize images.

BrainMAP offers a fresh approach to studying how brain regions interact during tasks.