This vision paper proposes KGNet, an on-demand graph machine learning (GML) as a service on top of RDF engines to support GML-enabled SPARQL queries. KGNet automates the training of GML models on a KG by identifying a task-specific subgraph. This helps reduce the task-irrelevant KG structure and properties for better scalability and accuracy. While training a GML model on KG, KGNet collects metadata of trained models in the form of an RDF graph called KGMeta, which is interlinked with the relevant subgraphs in KG. Finally, all trained models are accessible via a SPARQL-like query. We call it a GML-enabled query and refer to it as SPARQLML. KGNet supports SPARQLML on top of existing RDF engines as an interface for querying and inferencing over KGs using GML models. The development of KGNet poses research opportunities in several areas, including meta-sampling for identifying task-specific subgraphs, GML pipeline automation with computational constraints, such as limited time and memory budget, and SPARQLML query optimization. KGNet supports different GML tasks, such as node classification, link prediction, and semantic entity matching. We evaluated KGNet using two real KGs of different application domains. Compared to training on the entire KG, KGNet significantly reduced training time and memory usage while maintaining comparable or improved accuracy. The KGNet source-code is available for further study

翻译：本文提出一种知识图谱网络（KGNet）——基于RDF引擎的按需图机器学习即服务架构，旨在支持启用图机器学习的SPARQL查询。KGNet通过识别任务特定子图，自动完成知识图谱上GML模型的训练，从而减少与任务无关的知识图谱结构与属性，提升可扩展性与准确性。在训练过程中，KGNet将训练模型的元数据以RDF图形式（称为KGMeta）收集，并与知识图谱中相关子图建立关联。最终，所有训练模型可通过类SPARQL查询访问，我们将这种启用GML的查询称为SPARQLML。KGNet基于现有RDF引擎支持SPARQLML，提供利用GML模型对知识图谱进行查询与推理的接口。KGNet的开发在多个领域带来研究机遇，包括用于识别任务特定子图的元采样、受计算约束（如有限时间与内存预算）的GML流水线自动化，以及SPARQLML查询优化。KGNet支持多种GML任务，如节点分类、链路预测与语义实体匹配。我们使用两个不同应用领域的真实知识图谱对KGNet进行评估。与在整个知识图谱上训练相比，KGNet在保持相当或更优精度的同时，显著降低了训练时间与内存消耗。KGNet源代码可供进一步研究使用。