Graph Representation Learning methods opened new possibilities for addressing complex, real-world problems represented by graphs. However, many graphs used in these applications comprise millions of nodes and billions of edges and are beyond the capabilities of current methods and software implementations. We present GRAPE, a software resource for graph processing and representation learning that is able to scale with big graphs by using specialized and smart data structures, algorithms, and a fast parallel implementation. When compared with state of the art software resources, GRAPE shows an improvement of orders of magnitude in empirical space and time complexity, as well as a substantial and statistically significant improvement in edge prediction and node label prediction performance. Furthermore, GRAPE provides over 80, 000 graphs from the literature and other sources, standardized interfaces allowing a straightforward integration of third-party libraries, 61 node embedding methods, 25 inference models, and 3 modular pipelines to allow a FAIR and reproducible comparison of methods and libraries for graph processing and embedding.
翻译:“GRAPE”是一个用于图形处理和演示学习的软件资源,能够通过使用专门和智能数据结构、算法和快速平行实施的方式与大图表进行缩放。与最新软件资源相比,“GRAPE”显示在经验空间和时间复杂性方面改进了数量级,并在边缘预测和节点标签预测性能方面作了重大和统计上显著的改进。此外,GRAPE提供了80 000多张文献和其他来源的图表、标准化界面,使第三方图书馆能够直接整合,61个节点嵌入方法,25个推断模型,以及3个模块式管道,以便能够对图表处理和嵌入的方法和图书馆进行FAIR和可复制的比较。