mlsanityData to 7 Oct 2026

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

arXiv 2403.05752 ↗First posted 9 Mar 2024cs.LG cs.AIcited by 5

Not on the map. Why?

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 9 Mar 2024.

Builds on

29 of 52 references.

References · 29

  1. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  3. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  4. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  5. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  6. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  7. 2020Heterogeneous Graph Transformercited by 581
  8. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  9. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  10. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  11. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  12. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
17 more
  1. 2019AliGraph: A Comprehensive Graph Neural Network Platformcited by 152
  2. 2020DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphscited by 139
  3. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  4. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  5. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  6. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  7. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  8. 2020Scalable Graph Neural Networks for Heterogeneous Graphscited by 31
  9. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
  10. 2021Marius: Learning Massive Graph Embeddings on a Single Machinecited by 29
  11. 2022Multiplex Heterogeneous Graph Convolutional Networkcited by 27
  12. 2021Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNscited by 22
  13. 2022TF-GNN: Graph Neural Networks in TensorFlowcited by 21
  14. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  15. 2022Influence-Based Mini-Batching for Graph Neural Networkscited by 15
  16. 2023Link Prediction on Latent Heterogeneous Graphscited by 5
  17. 2023Towards a GML-Enabled Knowledge Graph Platformcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2025K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Predictioncited by 6
  2. 2026An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphscited by 2
  3. 2026Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphscited by 2
  4. 2024BSG4Bot: Efficient Bot Detection based on Biased Heterogeneous Subgraphscited by 1
  5. 2025gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphscited by 0