Saved in:
Bibliographic Details
Main Authors: Liang, Chumeng, Jin, Zhanyang, Akhtar, Zahaib, Pereira, Mona, Yu, Haofei, You, Jiaxuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.22903
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908735347097600
author Liang, Chumeng
Jin, Zhanyang
Akhtar, Zahaib
Pereira, Mona
Yu, Haofei
You, Jiaxuan
author_facet Liang, Chumeng
Jin, Zhanyang
Akhtar, Zahaib
Pereira, Mona
Yu, Haofei
You, Jiaxuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22903
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Debugging Tabular Log as Dynamic Graphs
Liang, Chumeng
Jin, Zhanyang
Akhtar, Zahaib
Pereira, Mona
Yu, Haofei
You, Jiaxuan
Machine Learning
Computation and Language
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.
title Debugging Tabular Log as Dynamic Graphs
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2512.22903