CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection

TL;DR

This paper introduces CACL, a community-aware contrastive learning framework for social media bot detection that leverages heterogeneous graphs and community information to improve detection accuracy and generalization.

Contribution

The paper proposes a novel community-aware heterogeneous graph contrastive learning method that dynamically mines hard samples and enhances graph representations for bot detection.

Findings

Outperforms baseline methods on three social media bot benchmarks.

Effectively mines hard positive and negative samples using community-aware modules.

Addresses over-smoothness and generalization issues in GNN-based bot detection.

Abstract

Social media bot detection is increasingly crucial with the rise of social media platforms. Existing methods predominantly construct social networks as graph and utilize graph neural networks (GNNs) for bot detection. However, most of these methods focus on how to improve the performance of GNNs while neglecting the community structure within social networks. Moreover, GNNs based methods still face problems such as poor model generalization due to the relatively small scale of the dataset and over-smoothness caused by information propagation mechanism. To address these problems, we propose a Community-Aware Heterogeneous Graph Contrastive Learning framework (CACL), which constructs social network as heterogeneous graph with multiple node types and edge types, and then utilizes community-aware module to dynamically mine both hard positive samples and hard negative samples for supervised graph contrastive learning with adaptive graph enhancement algorithms. Extensive experiments demonstrate that our framework addresses the previously mentioned challenges and outperforms competitive baselines on three social media bot benchmarks.