SOURCE-LINKED INTELLIGENCE

Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Dynamic networks are being applied in many domains, from social media to logistics systems, each with their own set of special characteristics. A model employed on this type of data must capture the duality between temporal/structural and feature-based information. Yet state-of-the-art deep learning models often struggle to learn especially short-term behavioral interaction signals, such as sender intensity or interaction inertia, directly from raw event streams. To address this gap, we propose a statistical feature augmentation method that explicitly encodes behavioral interaction statistics

Read original source ↗ Open in workspace

recordType

paper

region

Global