Towards Automatic Network Diagram Comprehension

• Published in: Proceedings - International Conference on Network Protocols pp. 1 - 15
• Main Authors: Ren, Yanyu, Miao, Yukai, Chen, Li, Li, Dan, Wang, Xizheng, Bai, Yu, Wu, Zhiyuan, Long, Fei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22.09.2025
• Subjects: AI for Networking; Automatic Network Diagram Comprehension; Benchmark testing; Data mining; Information retrieval; Knowledge engineering; Measurement; Multi-modal LLMs; Network Diagram; Network topology; Noise reduction; Pipelines; Protocols
• ISSN: 2643-3303
• DOI: 10.1109/ICNP65844.2025.11192381

Network Diagram Comprehension (NDC) is a vital task for networking professionals, offering essential insights into network topology and configurations. However, NDC remains a labor-intensive process heavily reliant on human expertise, with existing tools falling short in addressing this challenge. It is critical to develop an Automatic NDC (ANDC) system that ensures high faithfulness and completeness in information extraction while supporting practical, end-to-end NDC applications. Moreover, a comprehensive dataset and benchmark are necessary to systematically evaluate and drive the progress of ANDC.In this work, we introduce Layered Extractor of Network Diagrams (LEND), the first ANDC system designed to comprehensively and faithfully extract and utilize information from network diagrams. LEND employs a three-stage pipeline: (1) a layer extractor to decompose diagrams and identify key elements with a denoising cascade, (2) an inter-layer combiner to reconstruct entity relations with positional and domain knowledge, and (3) a task-specific interpreter for networking applications.To support this effort, we develop two extensive NDC datasets comprising over 4,000 network diagrams and icons from diverse sources, along with the first benchmark to evaluate ANDC systems across three distinct metrics. Empirical experiments demonstrate that LEND outperforms existing methods by achieving at 1.21- 5.10× better faithfulness and completeness, and improves its capability as a NetOps engineer by 30.5% on the Cisco Certified Network Associate (CCNA) exam.