通过智能筛选减少大模型调用，加速图上节点任务推理
Scaling GraphLLM with Bilevel-Optimized Sparse Querying
- 设计双层优化的稀疏查询策略，按需调用大模型
- 在六大数据集上速度远超现有方法，性能持平或更优
- 适合需要高效处理大规模文本图的科研与工业场景
大语言模型在文本属性图（TAGs）的节点级任务中展现出强大潜力，能提供解释性特征。然而，重复调用大模型带来高昂的计算与成本开销。例如，仅对包含48,000个节点的Photo数据集使用典型方法（如TAPE）生成全部节点解释，需数天时间。本文提出一种通用框架BOSQ（双层优化稀疏查询），通过自适应地选择性调用大模型解释特征，显著降低计算开销。在六个真实世界文本属性图数据集、两种节点级任务上进行的大量实验表明，BOSQ在大幅缩短运行时间的同时，性能保持相当或更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。