Boosting Bot Detection via Heterophily-Aware Representation Learning and Prototype-Guided Cluster Discovery

2025-06-01

AI Summary

Social bot detection suffers from strong label dependency, poor cross-community generalization, and limitations of existing generative graph self-supervised methods—which overly rely on the homophily assumption and fail to capture global heterophilous patterns. Method: We propose BotHP, the first framework integrating heterogeneity-aware representation learning with prototype-guided cluster discovery to transcend homophily constraints and model semantically coherent yet distributionally dispersed bot clusters. It employs a dual-encoder architecture, heterogeneity-enhanced contrastive learning, and generative graph self-supervised pretraining for robust weakly supervised detection. Contributions/Results: Evaluated on two real-world datasets, BotHP significantly boosts performance across diverse graph-based detectors, reduces labeling requirements, enhances cross-community generalization, and demonstrates resilience against interaction-based adversarial camouflage attacks.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Detecting social media bots is essential for maintaining the security and trustworthiness of social networks. While contemporary graph-based detection methods demonstrate promising results, their practical application is limited by label reliance and poor generalization capability across diverse communities. Generative Graph Self-Supervised Learning (GSL) presents a promising paradigm to overcome these limitations, yet existing approaches predominantly follow the homophily assumption and fail to capture the global patterns in the graph, which potentially diminishes their effectiveness when facing the challenges of interaction camouflage and distributed deployment in bot detection scenarios. To this end, we propose BotHP, a generative GSL framework tailored to boost graph-based bot detectors through heterophily-aware representation learning and prototype-guided cluster discovery. Specifically, BotHP leverages a dual-encoder architecture, consisting of a graph-aware encoder to capture node commonality and a graph-agnostic encoder to preserve node uniqueness. This enables the simultaneous modeling of both homophily and heterophily, effectively countering the interaction camouflage issue. Additionally, BotHP incorporates a prototype-guided cluster discovery pretext task to model the latent global consistency of bot clusters and identify spatially dispersed yet semantically aligned bot collectives. Extensive experiments on two real-world bot detection benchmarks demonstrate that BotHP consistently boosts graph-based bot detectors, improving detection performance, alleviating label reliance, and enhancing generalization capability.

Problem

• Detecting social media bots to enhance network security
• Overcoming label reliance and poor generalization in bot detection
• Addressing interaction camouflage and distributed bot deployment challenges

Innovation

• Heterophily-aware representation learning for bot detection
• Dual-encoder architecture modeling homophily and heterophily
• Prototype-guided cluster discovery for global consistency