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 2603.04545cs.LGcs.DB
收藏

面向大规模知识图谱的LLM引导的查询感知推理系统

An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

Concordia University(康科德大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校)

Waleed Afandi, Hussein Abdallah, Ashraf Aboulnaga, Essam Mansour

AI总结:

本文提出KG-WISE框架,通过将GNN模型分解为细粒度组件,并利用大语言模型生成查询模板,实现查询感知的高效推理,提升推理速度和降低内存使用。

摘要:

图神经网络(GNN)在大规模知识图谱(KGs)上的高效推理对许多实际应用至关重要。GNN推理查询计算成本高且复杂度各异,因为每个查询涉及不同数量的目标节点,这些节点连接到密度和结构各异的子图。现有加速方法如剪枝、量化和知识蒸馏虽然能生成小型模型,但无法适应个别查询的结构或语义。它们还存储模型为单体文件,必须完全加载,错过了仅加载与目标节点语义相关邻接节点和相应模型组件的机会。这些限制导致在大规模KGs上加载数据过多和计算冗余。本文提出KG-WISE,一种针对大规模KGs的任务驱动推理范式。KG-WISE将训练好的GNN模型分解为细粒度组件,根据查询子图的结构部分加载。它利用大语言模型(LLMs)生成可重用的查询模板,提取每个任务的语义相关子图,实现查询感知和紧凑模型实例化。我们在六个具有最多4200万节点和1.66亿条边的大规模KGs上评估了KG-WISE。KG-WISE在保持或提高准确性的同时,比最先进的系统快28倍,内存使用降低98%。

英文摘要:

Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference queries are computationally expensive and vary in complexity, as each involves a different number of target nodes linked to subgraphs of diverse densities and structures. Existing acceleration methods, such as pruning, quantization, and knowledge distillation, instantiate smaller models but do not adapt them to the structure or semantics of individual queries. They also store models as monolithic files that must be fully loaded, and miss the opportunity to retrieve only the neighboring nodes and corresponding model components that are semantically relevant to the target nodes. These limitations lead to excessive data loading and redundant computation on large KGs. This paper presents KG-WISE, a task-driven inference paradigm for large KGs. KG-WISE decomposes trained GNN models into fine-grained components that can be partially loaded based on the structure of the queried subgraph. It employs large language models (LLMs) to generate reusable query templates that extract semantically relevant subgraphs for each task, enabling query-aware and compact model instantiation. We evaluate KG-WISE on six large KGs with up to 42 million nodes and 166 million edges. KG-WISE achieves up to 28x faster inference and 98% lower memory usage than state-of-the-art systems while maintaining or improving accuracy across both commercial and open-weight LLMs.

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。

↑