--- id: ogb version: "1.3.6" license: MIT license_treatment: permissive maintenance: aging --- # ogb — Open Graph Benchmark License: permissive · Maintenance: aging · Downloads: 116.0K/mo ## What it is and what it does OGB is a collection of standardized benchmark datasets and tools for evaluating graph machine learning methods. It provides easy-to-use data loaders compatible with popular graph deep learning frameworks, handling dataset downloading, standardized train/validation/test splits, and unified evaluation metrics. The package covers three core graph ML tasks—node prediction, link prediction, and graph prediction—across datasets of varying scales (from single-GPU to multi-GPU) and diverse domains including scientific networks, social networks, and heterogeneous knowledge graphs. The package is designed to enable reliable comparison of different graph neural network methods by providing consistent dataset preparation and evaluation protocols. Researchers use OGB to benchmark their models against established baselines on real-world graph problems, avoiding the friction of manual dataset curation and metric implementation. Use it for: - Benchmark a new graph neural network architecture against standardized datasets and compare results using OGB's unified evaluators. - Download and prepare graph datasets with automatic splitting for training node, link, or graph classification models. - Evaluate graph ML methods on datasets spanning different scales and domains without manual preprocessing. - Reproduce published results on OGB benchmarks to validate research or baseline implementations. - Access diverse real-world graphs from scientific, social, and knowledge-graph domains for algorithm development. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. OGB provides standardized benchmark datasets, data loaders, and evaluators for graph machine learning tasks across node, link, and graph prediction problems. Yes, if you are working on graph neural networks and need standardized benchmarks. The package is well-established with 2093 GitHub stars, has no known vulnerabilities, and provides genuine value through unified data loading and evaluation. However, maintenance is aging (last release 2023-04-07)—verify compatibility with your PyTorch and graph framework versions before relying on it for new research. ## Install pip install ogb uv add ogb poetry add ogb ## Installing ogb Before you install: Low install friction with a pure-Python wheel. Maintenance is aging—last release was 2023-04-07, over 1225 days ago—but the repository remains active with 2093 stars and recent commits. Dependencies are stable and widely used. License in practice: MIT license is permissive, allowing commercial and private use with minimal restrictions. You must include a copy of the license and copyright notice. Quickstart: pip install ogb from ogb.graphproppred import PygGraphPropPredDataset dataset = PygGraphPropPredDataset(name='ogbg-molhiv') split_idx = dataset.get_idx_split() Requires PyTorch>=1.6 and either DGL>=0.5.0 or torch-geometric>=2.0.2 installed separately; OGB itself does not bundle these. Verify before relying: - Whether the aging maintenance status affects compatibility with recent PyTorch or graph framework versions. - Current test coverage and whether benchmarks remain aligned with modern graph ML research standards. - Actual monthly download volume and whether the 2093 GitHub stars reflect active research adoption. ## Package facts - License: MIT (permissive) - Python support: unspecified - Install friction: low - Maintenance: aging - Downloads: 116.0K/month (top 15,000 on PyPI) - Known vulnerabilities: none known ## Tags graph neural network benchmarks, graph machine learning datasets, GNN evaluation framework, graph dataset loader, benchmark graph data, graph ml evaluation, standardized graph datasets, graph-neural-networks, benchmark-datasets, ml-evaluation [View on SkillFed](https://skillfed.io/packages/ogb) · [View on PyPI](https://pypi.org/project/ogb/)