BotSCL: Heterophily-aware Social Bot Detection with Supervised Contrastive Learning

TL;DR

BotSCL introduces a heterophily-aware contrastive learning framework for social bot detection, effectively differentiating bot and human accounts by addressing heterophilic relations in social networks, leading to improved detection accuracy.

Contribution

The paper proposes a novel heterophily-aware contrastive learning method with graph augmentation and a specialized encoder for social bot detection, surpassing existing approaches.

Findings

Outperforms state-of-the-art bot detection methods

Effectively handles heterophilic relations in social networks

Achieves superior accuracy on benchmark datasets

Abstract

Detecting ever-evolving social bots has become increasingly challenging. Advanced bots tend to interact more with humans as a camouflage to evade detection. While graph-based detection methods can exploit various relations in social networks to model node behaviors, the aggregated information from neighbors largely ignore the inherent heterophily, i.e., the connections between different classes of accounts. Message passing mechanism on heterophilic edges can lead to feature mixture between bots and normal users, resulting in more false negatives. In this paper, we present BotSCL, a heterophily-aware contrastive learning framework that can adaptively differentiate neighbor representations of heterophilic relations while assimilating the representations of homophilic neighbors. Specifically, we employ two graph augmentation methods to generate different graph views and design a channel-wise and attention-free encoder to overcome the limitation of neighbor information summing. Supervised contrastive learning is used to guide the encoder to aggregate class-specific information. Extensive experiments on two social bot detection benchmarks demonstrate that BotSCL outperforms baseline approaches including the state-of-the-art bot detection approaches, partially heterophilic GNNs and self-supervised contrast learning methods.