arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.08952cs.LG
收藏

当大语言模型代理遇见图优化:一种自动化数据质量改进方法

When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach

Shenzhen Institute of Technology(深圳理工大学)

Zhihan Zhang, Xunkai Li, Yilong Zuo, Yanzhe Wen, Zhaoxin Fan, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang

AI总结:

LAGA是一种统一的多代理框架,通过协调多模态优化全面提升文本属性图的数据质量,验证了数据驱动的质量优化在可靠分析中的重要性。

摘要:

文本属性图(TAGs)已成为现代数据管理和分析中关键的图结构数据形式,结合了结构关系与丰富的文本语义,用于各种应用。然而,分析模型的有效性,特别是图神经网络(GNNs),对数据质量非常敏感。我们的实证分析表明,传统和增强大语言模型的GNNs在文本、结构和标签不完美情况下显著退化,凸显TAG质量作为可靠分析的关键瓶颈。现有研究已探索了TAGs的数据级优化,但大多数专注于特定退化类型并针对单一方面如结构或标签,缺乏对数据质量改进的系统和全面视角。为解决这一差距,我们提出LAGA(大语言和图代理),一种统一的多代理框架,用于全面的TAG质量优化。LAGA将图质量控制视为以数据为中心的过程,将检测、规划、行动和评估代理整合到一个自动化循环中。通过协调多模态优化,全面增强文本、结构和标签方面。在5个数据集和16个基线模型上进行的广泛实验,涵盖了9种场景,证明了LAGA的有效性、鲁棒性和可扩展性,确认了以数据为中心的质量优化对于可靠TAG分析的重要性。

英文摘要:

Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantics for diverse applications. However, the effectiveness of analytical models, particularly graph neural networks (GNNs), is highly sensitive to data quality. Our empirical analysis shows that both conventional and LLM-enhanced GNNs degrade notably under textual, structural, and label imperfections, underscoring TAG quality as a key bottleneck for reliable analytics. Existing studies have explored data-level optimization for TAGs, but most focus on specific degradation types and target a single aspect like structure or label, lacking a systematic and comprehensive perspective on data quality improvement. To address this gap, we propose LAGA (Large Language and Graph Agent), a unified multi-agent framework for comprehensive TAG quality optimization. LAGA formulates graph quality control as a data-centric process, integrating detection, planning, action, and evaluation agents into an automated loop. It holistically enhances textual, structural, and label aspects through coordinated multi-modal optimization. Extensive experiments on 5 datasets and 16 baselines across 9 scenarios demonstrate the effectiveness, robustness and scalability of LAGA, confirming the importance of data-centric quality optimization for reliable TAG analytics.

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。

↑