Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection
This addresses bot detection for social network security, but it is incremental as it adapts existing over-sampling techniques to GNNs.
The paper tackled the problem of class-imbalanced bot detection in online social networks using graph neural networks, proposing an over-sampling strategy in feature space that avoids edge synthesis, and it showed consistent superiority over baselines on three real-world datasets.
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.