Towards a GML-Enabled Knowledge Graph Platform
Not on the map. Why?
Abstract (arXiv)
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
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 3 Mar 2023.
Builds on
27 of 55 references.
References · 27
- 2017Inductive Representation Learning on Large Graphscited by 6,303
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
- 2017Billion-scale similarity search with GPUscited by 2,490
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,157
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,915
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,689
- 2020Knowledge Graphscited by 619
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
- 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
- 2017The Case for Learned Index Structurescited by 188
15 more
- 2020DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphscited by 139
- 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
- 2022EIGNN: Efficient Infinite-Depth Graph Neural Networkscited by 32
- 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
- 2019Fast and Accurate Network Embeddings via Very Sparse Random Projectioncited by 29
- 2022Saga: A Platform for Continuous Construction and Serving of Knowledge At Scalecited by 18
- 2020Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognitioncited by 15
- 2021Scalable Graph Neural Network Training: The Case for Samplingcited by 11
- 2021r-GAT: Relational Graph Attention Network for Multi-Relational Graphscited by 9
- 2016Enabling Cognitive Intelligence Queries in Relational Databases using Low-dimensional Word Embeddingscited by 6
- 2017Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilitiescited by 6
- 2019Multi-Attribute Selectivity Estimation Using Deep Learningcited by 6
- 2019sql4ml A declarative end-to-end workflow for machine learningcited by 6
- 2022Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Cloudscited by 6
- 2020RDFFrames: Knowledge Graph Access for Machine Learning Toolscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.