SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection

TL;DR

SeBot introduces a novel multi-view contrastive learning approach guided by structural entropy to improve social bot detection, addressing limitations of previous graph-based methods and enhancing robustness against adversarial bots.

Contribution

The paper proposes SEBot, which leverages structural entropy for graph optimization and multi-view contrastive learning to improve social bot detection accuracy and robustness.

Findings

Significantly outperforms state-of-the-art methods.

Enhances robustness to adversarial social bots.

Utilizes structural entropy for hierarchical community detection.

Abstract

Recent advancements in social bot detection have been driven by the adoption of Graph Neural Networks. The social graph, constructed from social network interactions, contains benign and bot accounts that influence each other. However, previous graph-based detection methods that follow the transductive message-passing paradigm may not fully utilize hidden graph information and are vulnerable to adversarial bot behavior. The indiscriminate message passing between nodes from different categories and communities results in excessively homogeneous node representations, ultimately reducing the effectiveness of social bot detectors. In this paper, we propose SEBot, a novel multi-view graph-based contrastive learning-enabled social bot detector. In particular, we use structural entropy as an uncertainty metric to optimize the entire graph's structure and subgraph-level granularity, revealing the implicitly existing hierarchical community structure. And we design an encoder to enable message passing beyond the homophily assumption, enhancing robustness to adversarial behaviors of social bots. Finally, we employ multi-view contrastive learning to maximize mutual information between different views and enhance the detection performance through multi-task learning. Experimental results demonstrate that our approach significantly improves the performance of social bot detection compared with SOTA methods.