OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learning

TL;DR

OpenGDA is a comprehensive benchmark for graph domain adaptation that evaluates models across diverse tasks and scenarios, addressing current limitations in evaluation scope and scenario diversity.

Contribution

It introduces a unified, scalable benchmark with diverse datasets and standardized pipelines for evaluating graph domain adaptation models across multiple tasks and scenarios.

Findings

Highlights challenges in applying GDA models to real-world data.

Provides insights into model performance across different tasks.

Establishes a platform for future research and model comparison.

Abstract

Graph domain adaptation models are widely adopted in cross-network learning tasks, with the aim of transferring labeling or structural knowledge. Currently, there mainly exist two limitations in evaluating graph domain adaptation models. On one side, they are primarily tested for the specific cross-network node classification task, leaving tasks at edge-level and graph-level largely under-explored. Moreover, they are primarily tested in limited scenarios, such as social networks or citation networks, lacking validation of model's capability in richer scenarios. As comprehensively assessing models could enhance model practicality in real-world applications, we propose a benchmark, known as OpenGDA. It provides abundant pre-processed and unified datasets for different types of tasks (node, edge, graph). They originate from diverse scenarios, covering web information systems, urban systems and natural systems. Furthermore, it integrates state-of-the-art models with standardized and end-to-end pipelines. Overall, OpenGDA provides a user-friendly, scalable and reproducible benchmark for evaluating graph domain adaptation models. The benchmark experiments highlight the challenges of applying GDA models to real-world applications with consistent good performance, and potentially provide insights to future research. As an emerging project, OpenGDA will be regularly updated with new datasets and models. It could be accessed from https://github.com/Skyorca/OpenGDA.