LLMs enhance graph anomaly detection with structure-aware text embeddings

Researchers have developed TERGAD, a new framework for graph anomaly detection that leverages Large Language Models (LLMs). TERGAD translates a node's structural properties into natural language narratives, which are then processed by an LLM to generate semantic embeddings. These embeddings are fused with original node attributes to reconstruct both graph structure and node features, with anomalies identified by reconstruction errors. Experiments on six datasets show TERGAD outperforms existing methods. AI

IMPACT Enhances anomaly detection in complex graph data by integrating LLM-driven semantic understanding with structural analysis.

RANK_REASON The cluster contains a research paper detailing a novel framework for graph anomaly detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Large Language Models
• LLMs
• TERGAD

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →