PyTorch Geometric Signed Directed Documentation

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. It builds on open-source deep-learning and graph processing libraries. PyTorch Geometric Signed Directed consists of various signed and directed geometric deep learning, embedding, and clustering methods from a variety of published research papers and selected preprints.

Notes

• Installation
• Introduction
• Citing
• Data Structures
  • Data Classes
  • Benchmark Datasets
  • Node Splitting
  • Edge Splitting
• Case Study Examples
  • Case Study on Signed Networks
  • Case Study on Directed Networks
• External Resources
  • External Resources - Architectures
  • External Resources - Synthetic Data Generators
  • External Resources - Real-World Data Sets

Package Reference

• PyTorch Geometric Signed Directed Models
  • Directed Undirected Network Models and Layers
  • Signed (Directed) Network Models and Layers
  • Auxiliary Methods and Layers
• PyTorch Geometric Signed Directed Data Generators and Data Loaders
  • Data Classes
  • Data Generators
  • Data Loaders
• PyTorch Geometric Signed Directed Utils
  • Task-Specific Objectives and Evaluation Methods
  • Utilities and Preprocessing Methods