基于动态图的表格日志调试
Debugging Tabular Log as Dynamic Graphs
AI总结：
本文提出GraphLogDebugger框架，利用动态图模型高效调试表格日志，优于大型语言模型。
摘要：
表格日志抽象了现实系统中的对象和事件，并报告其更新以反映系统的变化，其中可以通过调试相应的日志条目来高效检测现实中的不一致。然而，近年来处理文本丰富型表格日志数据的进展过于依赖大型语言模型（LLMs）和其他重型模型，从而导致灵活性和可扩展性受限。本文提出了一种新的框架，GraphLogDebugger，用于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的边，该框架将表格日志背后的系统恢复为一个演化的动态图。借助我们的动态图建模，一个简单的动态图神经网络（GNN）具有足够的代表性，能够在调试表格日志中优于LLMs，这在计算机系统和学术论文的真实日志数据集上得到了实验验证。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
