Abstract:LLMs have recently shown strong potential in enhancing node-level tasks on text-attributed graphs (TAGs) by providing explanation features. However, their practical use is severely limited by the high computational and monetary cost of repeated LLM queries. To illustrate, naively generating explanations for all nodes on a medium-sized benchmark like Photo (48k nodes) using a representative method (e.g., TAPE) would consume days of processing time. In this paper, we propose Bilevel-Optimized Sparse Querying (BOSQ), a general framework that selectively leverages LLM-derived explanation features to enhance performance on node-level tasks on TAGs. We design an adaptive sparse querying strategy that selectively decides when to invoke LLMs, avoiding redundant or low-gain queries and significantly reducing computation overhead. Extensive experiments on six real-world TAG datasets involving two types of node-level tasks demonstrate that BOSQ runs substantially faster than existing GraphLLM methods while consistently delivering on-par or superior performance.
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.09038 [cs.DB] |
| (or arXiv:2602.09038v2 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2602.09038 arXiv-issued DOI via DataCite |
From: Yangzhe Peng [view email]
[v1]
Fri, 30 Jan 2026 07:03:18 UTC (242 KB)
[v2]
Tue, 26 May 2026 11:54:59 UTC (303 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。