IEEE

Adversarial Attack and Defense on Discrete Time Dynamic Graphs

Abstract: Graph learning methods have achieved remarkable performance in various domains such as social recommendation, financial fraud detection, and so on. In real applications, the underlying graph ...
GitHub

An easy-to-use bulk hold-time analyzer, generating graphs for the hold times of osu!standard replays.

To get started, head over to the latest release page on GitHub. From there, locate and download the ZIP file (ending with .zip). Once the download is complete, extract the ZIP file. On the first start ...
GitHub

GraphStorm: Enterprise graph machine learning framework for billion-scale graphs

GraphStorm is an enterprise-grade graph machine learning (GML) framework designed for scalability and ease of use. It simplifies the development and deployment of GML models on industry-scale graphs ...
IEEE

Fusion Graph Structure Learning-Based Multivariate Time Series Anomaly Detection With Structured Prior Knowledge

Abstract: Multivariate time series anomaly detection (MTSAD) plays a crucial role in the Internet of Things (IoT) to identify device malfunction or system attacks. Graph neural networks (GNN) are ...