Muti-scale Graph Neural Network with Signed-attention for Social Bot Detection: A Frequency Perspective

TL;DR

This paper introduces MSGS, a multi-scale graph neural network with signed-attention that effectively captures both high and low-frequency information in social graphs, improving social bot detection accuracy.

Contribution

The paper proposes a novel multi-scale graph neural network with signed-attention that leverages both high and low-frequency information for enhanced social bot detection.

Findings

MSGS outperforms existing methods on real-world datasets.

MSGS effectively utilizes high-frequency information to prevent over-smoothing.

The approach demonstrates improved detection accuracy over state-of-the-art models.

Abstract

The presence of a large number of bots on social media has adverse effects. The graph neural network (GNN) can effectively leverage the social relationships between users and achieve excellent results in detecting bots. Recently, more and more GNN-based methods have been proposed for bot detection. However, the existing GNN-based bot detection methods only focus on low-frequency information and seldom consider high-frequency information, which limits the representation ability of the model. To address this issue, this paper proposes a Multi-scale with Signed-attention Graph Filter for social bot detection called MSGS. MSGS could effectively utilize both high and low-frequency information in the social graph. Specifically, MSGS utilizes a multi-scale structure to produce representation vectors at different scales. These representations are then combined using a signed-attention mechanism. Finally, multi-scale representations via MLP after polymerization to produce the final result. We analyze the frequency response and demonstrate that MSGS is a more flexible and expressive adaptive graph filter. MSGS can effectively utilize high-frequency information to alleviate the over-smoothing problem of deep GNNs. Experimental results on real-world datasets demonstrate that our method achieves better performance compared with several state-of-the-art social bot detection methods.