arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.05752cs.LGcs.AI
收藏

在大知识图谱上进行面向任务的GNNs训练以实现准确高效的建模

Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling

Concordia University(康考迪亚大学);KAUST(阿卜杜拉国王科技大学)

Hussein Abdallah, Waleed Afandi, Panos Kalnis, Essam Mansour

AI总结:

本文提出KG-TOSA方法,通过自动提取面向任务的子图(TOSG)来优化大型知识图谱上的HGNN训练,在将训练时间和内存使用量减少高达70%的同时提升模型准确率和推理速度。

摘要:

知识图谱(KG)是一种包含多种节点和边类型的异构图。异构图神经网络(HGNNs)常用于在KG上训练节点分类和链接预测等机器学习任务。然而,HGNN方法的复杂度过高,受KG的大小、密度以及节点和边类型数量的影响。AI从业者会手工构建与特定任务相关的KG G的子图。我们将此子图称为面向任务的子图(TOSG),它包含G中与任务相关的节点和边类型的子集。使用TOSG代替G来训练任务,可以减轻大型KG所需的过度计算。然而,构建TOSG需要对KG的结构和任务目标有深入的理解,因此既具挑战性又耗时。本文提出了KG-TOSA,一种自动化提取TOSG的方法,用于在大型KG上进行面向任务的HGNN训练。在KG-TOSA中,我们定义了一种通用图模式,用于捕获与特定任务相关的KG局部和全局结构。我们探索了提取匹配该图模式的子图的不同技术:即(i)使用偏置随机游走或影响分数在目标节点周围采样的两种技术,以及(ii)利用RDF引擎内置索引的基于SPARQL的提取方法。因此,与采样技术相比,它实现了可忽略不计的预处理开销。我们开发了一个包含大型真实KG以及用于节点分类和链接预测的各种任务的基准。实验表明,KG-TOSA帮助最先进的HGNN方法将训练时间和内存使用量减少高达70%,同时提升了模型性能,例如准确率和推理时间。

英文摘要:

A Knowledge Graph (KG) is a heterogeneous graph encompassing a diverse range of node and edge types. Heterogeneous Graph Neural Networks (HGNNs) are popular for training machine learning tasks like node classification and link prediction on KGs. However, HGNN methods exhibit excessive complexity influenced by the KG's size, density, and the number of node and edge types. AI practitioners handcraft a subgraph of a KG G relevant to a specific task. We refer to this subgraph as a task-oriented subgraph (TOSG), which contains a subset of task-related node and edge types in G. Training the task using TOSG instead of G alleviates the excessive computation required for a large KG. Crafting the TOSG demands a deep understanding of the KG's structure and the task's objectives. Hence, it is challenging and time-consuming. This paper proposes KG-TOSA, an approach to automate the TOSG extraction for task-oriented HGNN training on a large KG. In KG-TOSA, we define a generic graph pattern that captures the KG's local and global structure relevant to a specific task. We explore different techniques to extract subgraphs matching our graph pattern: namely (i) two techniques sampling around targeted nodes using biased random walk or influence scores, and (ii) a SPARQL-based extraction method leveraging RDF engines' built-in indices. Hence, it achieves negligible preprocessing overhead compared to the sampling techniques. We develop a benchmark of real KGs of large sizes and various tasks for node classification and link prediction. Our experiments show that KG-TOSA helps state-of-the-art HGNN methods reduce training time and memory usage by up to 70% while improving the model performance, e.g., accuracy and inference time.

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。

↑