PyGDA：面向图域自适应的Python库

PyGDA: A Python Library for Graph Domain Adaptation

March 13, 2025

作者: Zhen Zhang, Meihan Liu, Bingsheng He

cs.AI

摘要

图域适应作为一种促进跨领域知识迁移的有前景方法，近年来已崭露头角。近期，众多模型被提出以增强该领域的泛化能力。然而，目前尚缺乏一个统一库来整合现有技术并简化其实现。为填补这一空白，我们推出了PyGDA，一款专为图域适应设计的开源Python库。作为该领域的首个综合性库，PyGDA涵盖了超过20种广泛使用的图域适应方法及多种类型的图数据集。具体而言，PyGDA提供了模块化组件，使用户能够利用一系列常用实用功能无缝构建定制模型。为处理大规模图数据，PyGDA支持采样和小批量处理等特性，确保计算效率。此外，PyGDA还包含了全面的性能基准测试以及为研究人员和从业者精心编写的用户友好API文档。为便于广泛使用，PyGDA以MIT许可证发布于https://github.com/pygda-team/pygda，API文档则位于https://pygda.readthedocs.io/en/stable/。

English

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/.