Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection
OS-GNN generates minority-class feature-space samples via neighborhood aggregation for graph-based bot detection, outperforming baselines without edge synthesis.
Published Feb 14, 20232 citationsarXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
OS-GNN offers a sharp, edge-free feature-space fix for imbalanced bot detection that avoids graph corruption, though its missing overhead metrics, thin benchmarks, and unverified production readiness leave its practical value uncertain.
Abstract
The presence of a large number of bots in Online Social Networks (OSN) leads to undesirable social effects. Graph neural networks (GNNs) are effective in detecting bots as they utilize user interactions. However, class-imbalanced issues can affect bot detection performance. To address this, we propose an over-sampling strategy for GNNs (OS-GNN) that generates samples for the minority class without edge synthesis. First, node features are mapped to a feature space through neighborhood aggregation. Then, we generate samples for the minority class in the feature space. Finally, the augmented features are used to train the classifiers. This framework is general and can be easily extended into different GNN architectures. The proposed framework is evaluated using three real-world bot detection benchmark datasets, and it consistently exhibits superiority over the baselines.