OGBDatasetLoader<T>

Models & Types · AiDotNet.Data.Graph

Loads datasets from the Open Graph Benchmark (OGB) for standardized evaluation.

Inheritance: DataLoaderBase<T> → GraphDataLoaderBase<T> → OGBDatasetLoader<T>

For Beginners

OGB provides standard benchmarks for fair comparison.

What is OGB?

  • Collection of real-world graph datasets
  • Standardized train/val/test splits
  • Automated evaluation metrics
  • Enables fair comparison between different GNN methods

Why OGB matters:

  • Reproducibility: Everyone uses same data splits
  • Realism: Real-world graphs, not toy datasets
  • Scale: Large graphs that test scalability
  • Diversity: Multiple domains and tasks

OGB Dataset Categories:

1. Node Property Prediction:

  • ogbn-arxiv: Citation network (169K papers)
  • ogbn-products: Amazon product co-purchasing network (2.4M products)
  • ogbn-proteins: Protein association network (132K proteins)

2. Link Property Prediction:

  • ogbl-collab: Author collaboration network
  • ogbl-citation2: Citation network
  • ogbl-ddi: Drug-drug interaction network

3. Graph Property Prediction:

  • ogbg-molhiv: Molecular graphs for HIV activity prediction (41K molecules)
  • ogbg-molpcba: Molecular graphs for biological assays (437K molecules)
  • ogbg-ppa: Protein association graphs

How It Works

The Open Graph Benchmark (OGB) is a collection of realistic, large-scale graph datasets with standardized evaluation protocols for graph machine learning research.

Constructors

Constructor Summary
OGBDatasetLoader(string datasetName, OGBTask<T> taskType, int batchSize, string dataPath, bool autoDownload) Initializes a new instance of the OGBDatasetLoader class.

Properties

Property Summary
int NumClasses { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
GraphClassificationTask<T> CreateGraphClassificationTask(double trainRatio, double valRatio, int? seed)
LinkPredictionTask<T> CreateLinkPredictionTask(double trainRatio, double negativeRatio, int? seed)
NodeClassificationTask<T> CreateNodeClassificationTask(double trainRatio, double valRatio, int? seed)