基于双层优化稀疏查询的GraphLLM扩展
Scaling GraphLLM with Bilevel-Optimized Sparse Querying
AI总结:
提出BOSQ框架,通过自适应稀疏查询策略选择性调用LLM,在降低计算成本的同时保持或提升图节点任务性能。
摘要:
LLMs最近通过提供解释特征,在文本属性图(TAGs)上增强节点级任务方面显示出强大潜力。然而,重复LLM查询的高计算和货币成本严重限制了其实际应用。举例来说,使用代表性方法(如TAPE)为中等规模基准(如Photo,48k节点)上的所有节点朴素生成解释将消耗数天的处理时间。在本文中,我们提出双层优化稀疏查询(BOSQ),一个通用框架,选择性利用LLM导出的解释特征来提升TAGs上节点级任务的性能。我们设计了一种自适应稀疏查询策略,选择性决定何时调用LLM,避免冗余或低增益查询,显著降低计算开销。在涉及两种节点级任务的六个真实世界TAG数据集上的大量实验表明,BOSQ比现有GraphLLM方法运行速度显著更快,同时持续提供相当或更优的性能。
英文摘要:
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.
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。