PyGDA: A Python Library for Graph Domain Adaptation
Zhen Zhang, Meihan Liu, Bingsheng He
TL;DR
The paper presents PyGDA, the first comprehensive Python library for graph domain adaptation, addressing the need for unified tooling across source-needed, source-free, and multi-source settings for both node- and graph-level tasks. It delivers a broad collection of over 20 algorithms, seven real-world datasets with standardized preprocessing, and a modular API built on PyTorch and PyG with scalable data handling through sampling and mini-batching. It incorporates benchmarking, thorough documentation, and ready-to-run tutorials to support reproducible experiments and rapid prototyping. By providing a standardized workflow and extensible infrastructure, PyGDA enables researchers and practitioners to compare methods, develop new approaches, and deploy graph domain adaptation pipelines at scale.
Abstract
Graph domain adaptation has emerged as a promising approach to facilitate knowledge transfer across different domains. Recently, numerous models have been proposed to enhance their generalization capabilities in this field. However, there is still no unified library that brings together existing techniques and simplifies their implementation. To fill this gap, we introduce PyGDA, an open-source Python library tailored for graph domain adaptation. As the first comprehensive library in this area, PyGDA covers more than 20 widely used graph domain adaptation methods together with different types of graph datasets. Specifically, PyGDA offers modular components, enabling users to seamlessly build custom models with a variety of commonly used utility functions. To handle large-scale graphs, PyGDA includes support for features such as sampling and mini-batch processing, ensuring efficient computation. In addition, PyGDA also includes comprehensive performance benchmarks and well-documented user-friendly API for both researchers and practitioners. To foster convenient accessibility, PyGDA is released under the MIT license at https://github.com/pygda-team/pygda, and the API documentation is https://pygda.readthedocs.io/en/stable/.