用动态图模型高效调试表格日志，效果优于大模型。
Debugging Tabular Log as Dynamic Graphs
- 将日志中的对象和事件建模为动态图节点，通过边连接构建演化图
- 仅用简单动态GNN就超越了大语言模型在真实系统日志上的调试表现
- 适合需要高效、可扩展日志调试的系统运维与科研人员
表格日志抽象了现实系统中的对象与事件，并报告其更新以反映系统变化，通过调试相应日志条目可高效发现现实不一致。然而，现有处理文本增强表格日志的方法过度依赖大语言模型（LLMs）等重型模型，导致灵活性与可扩展性受限。本文提出新框架 GraphLogDebugger，基于动态图调试表格日志。通过为对象和事件构建异构节点并连接节点间边，该框架将日志背后的系统还原为动态演化图。借助动态图建模，一个简单的动态图神经网络（GNN）已足够强大，在计算机系统与学术论文的真实日志数据集上，其调试性能优于大语言模型。
原文摘要 · Abstract (English)
Tabular log abstracts objects and events in the real-world system and reports their updates to reflect the change of the system, where one can detect real-world inconsistencies efficiently by debugging corresponding log entries. However, recent advances in processing text-enriched tabular log data overly depend on large language models (LLMs) and other heavy-load models, thus suffering from limited flexibility and scalability. This paper proposes a new framework, GraphLogDebugger, to debug tabular log based on dynamic graphs. By constructing heterogeneous nodes for objects and events and connecting node-wise edges, the framework recovers the system behind the tabular log as an evolving dynamic graph. With the help of our dynamic graph modeling, a simple dynamic Graph Neural Network (GNN) is representative enough to outperform LLMs in debugging tabular log, which is validated by experimental results on real-world log datasets of computer systems and academic papers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。