Abstract: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.
| Comments: | 36 pages, 11 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.08952 [cs.LG] |
| (or arXiv:2510.08952v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.08952 arXiv-issued DOI via DataCite |
From: Xunkai Li [view email]
[v1]
Fri, 10 Oct 2025 02:59:19 UTC (1,608 KB)
[v2]
Mon, 20 Oct 2025 04:17:41 UTC (1,608 KB)
[v3]
Sat, 31 Jan 2026 15:38:14 UTC (1,826 KB)
[v4]
Tue, 5 May 2026 05:35:19 UTC (1,932 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。