Reverse Dependencies of ogb

The following projects have a declared dependency on ogb:

• autogl — AutoML tools for graph-structure dataset
• big-graph-dataset — A collection of graph datasets in torch_geometric format.
• cogdl — An Extensive Research Toolkit for Deep Learning on Graphs
• cool-graph — Python library for building Graph Neural Network by few steps
• dglgo — DGL
• fedgraph — Federated Graph Learning
• ggfm — no summary
• grape-pi — Using graph neural networks to enhance protein identification using protein interaction networks.
• graph-ood — GOOD: A Graph Out-of-Distribution Benchmark
• graph4nlp — A DGL and PyTorch based graph deep learning library for natural language processing
• graph4nlp-cu101 — A DGL and PyTorch based graph deep learning library for natural language processing
• graph4nlp-cu102 — A DGL and PyTorch based graph deep learning library for natural language processing
• graph4nlp-cu110 — A DGL and PyTorch based graph deep learning library for natural language processing
• graph4nlp-cu92 — A DGL and PyTorch based graph deep learning library for natural language processing
• graphdatascience — A Python client for the Neo4j Graph Data Science (GDS) library
• graphgym — GraphGym: platform for designing and evaluating Graph Neural Networks (GNN)
• graphium — Graphium: Scaling molecular GNNs to infinity.
• graphslim — Slimming the graph data for graph learning
• graphstorm — GraphStorm
• GSLB — GSLB: Graph Structure Learning Benchmark
• H2GB — A graph benchmark library for heterophilic and heterogeneous graphs
• infoalign — A package for the paper: learning molecular representation in a cell
• libauc — LibAUC: A Deep Learning Library for X-Risk Optimization
• model2graph — A package to convert deep learning models into graph structures
• olorenchemengine — Oloren ChemEngine is a library for molecular property prediction, uncertainty quantification and interpretability. It includes 50+ models and molecular representations under a unified API, which achieves state-of-the-art performances on a variety of molecular property prediction tasks. The diversity of models and representations is achieved by integrating all top-performing methods in the literature as well an in-house methods.
• openhgnn — An open-source toolkit for Heterogeneous Graph Neural Network
• PyDGN — A Python Package for Deep Graph Networks
• pykeen — A package for training and evaluating multimodal knowledge graph embeddings
• sgl-dair — Graph Neural Network (GNN) toolkit targeting scalable graph learning
• spirograph — A tool to help building ML pipeline easier for non technical users..
• stark-qa — Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
• stars-omics — A spatial transcriptomics analysis tool.
• wilds — WILDS distribution shift benchmark