PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network

TL;DR

PyGHO is a unified, user-friendly library that simplifies the implementation of High Order Graph Neural Networks, offering significant speed improvements and reducing coding complexity for advanced GNN models.

Contribution

PyGHO provides the first standardized, flexible framework for HOGNNs, enabling easier development and comparison of high-order GNNs.

Findings

Achieves up to 50% acceleration in HOGNN computations.

Reduces implementation code by an order of magnitude.

Demonstrates competitive performance on real-world tasks.

Abstract

We introduce PyTorch Geometric High Order (PyGHO), a library for High Order Graph Neural Networks (HOGNNs) that extends PyTorch Geometric (PyG). Unlike ordinary Message Passing Neural Networks (MPNNs) that exchange messages between nodes, HOGNNs, encompassing subgraph GNNs and k-WL GNNs, encode node tuples, a method previously lacking a standardized framework and often requiring complex coding. PyGHO's main objective is to provide an unified and user-friendly interface for various HOGNNs. It accomplishes this through streamlined data structures for node tuples, comprehensive data processing utilities, and a flexible suite of operators for high-order GNN methodologies. In this work, we present a detailed in-depth of PyGHO and compare HOGNNs implemented with PyGHO with their official implementation on real-world tasks. PyGHO achieves up to $50\%$ acceleration and reduces the code needed for implementation by an order of magnitude. Our library is available at \url{https://github.com/GraphPKU/PygHO}.