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

arXiv: https://arxiv.org/abs/2403.05752 · HTML: https://mlsanity.com/paper/2403.05752/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 52 references that are in the map.
- First posted on arXiv 9 Mar 2024.

## Builds on (most cited first, 29 of 29)

- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments](https://mlsanity.com/paper/2206.10013/) (2022)
- [Sampling methods for efficient training of graph convolutional networks: A survey](https://mlsanity.com/paper/2103.05872/) (2021)
- [Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/2110.14170/) (2021)
- [Scalable Graph Neural Networks for Heterogeneous Graphs](https://mlsanity.com/paper/2011.09679/) (2020)
- [Marius: Learning Massive Graph Embeddings on a Single Machine](https://mlsanity.com/paper/2101.08358/) (2021)
- [Multiplex Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2208.06129/) (2022)
- [Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs](https://mlsanity.com/paper/2106.06218/) (2021)
- [TF-GNN: Graph Neural Networks in TensorFlow](https://mlsanity.com/paper/2207.03522/) (2022)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Influence-Based Mini-Batching for Graph Neural Networks](https://mlsanity.com/paper/2212.09083/) (2022)
- [Link Prediction on Latent Heterogeneous Graphs](https://mlsanity.com/paper/2302.10432/) (2023)
- [Towards a GML-Enabled Knowledge Graph Platform](https://mlsanity.com/paper/2303.02166/) (2023)

## Built on by (most cited first, 5 of 5)

- [K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction](https://mlsanity.com/paper/2502.13344/) (2025)
- [An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs](https://mlsanity.com/paper/2603.04545/) (2026)
- [Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2604.13979/) (2026)
- [BSG4Bot: Efficient Bot Detection based on Biased Heterogeneous Subgraphs](https://mlsanity.com/paper/2410.05356/) (2024)
- [gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs](https://mlsanity.com/paper/2512.08274/) (2025)

## Abstract (arXiv)

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.