arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.00552cs.LGcs.DC
收藏

图神经网络训练系统:全图与Mini-Batch的性能比较

Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batch

University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校)

Saurabh Bajaj, Hojae Son, Juelin Liu, Hui Guan, Marco Serafini

AI总结:

本文对代表性的full-graph和mini-batch GNN训练系统进行全面实证比较,发现mini-batch系统收敛更快且准确率不逊于full-graph,强调了跨类别比较、使用time-to-accuracy指标及分别调参的重要性。

摘要:

图神经网络(GNNs)因其学习图结构数据表示的能力而在近年来备受关注。训练GNN的两种常见方法是mini-batch训练和full-graph训练。由于这两种方法需要不同的训练流程和系统优化,因此出现了两类独立的GNN训练系统,每类系统分别针对其中一种方法定制。介绍某一特定类别系统的研究工作主要将其与同类别内的其他系统进行比较,而与另一类别的系统进行比较有限或没有比较。一些先前的工作也通过声称其比替代方法达到更高的准确率来证明其专注于一种特定训练方法的合理性。然而,文献在这方面的证据并不完整且相互矛盾。在本文中,我们对具有代表性的full-graph和mini-batch GNN训练系统进行了全面的实证比较。我们发现,在多个数据集、GNN模型和系统配置下,mini-batch训练系统的收敛速度始终快于full-graph训练系统。我们还发现,mini-batch训练技术的收敛准确率与full-graph训练技术相似或通常更高,这表明mini-batch采样不一定会损害准确率。我们的工作强调了跨不同类别比较系统的重要性,使用time-to-accuracy而非epoch time进行性能比较,以及为每种训练方法分别选择合适的超参数。

英文摘要:

Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to learn representations of graph-structured data. Two common methods for training GNNs are mini-batch training and full-graph training. Since these two methods require different training pipelines and systems optimizations, two separate classes of GNN training systems emerged, each tailored for one method. Works that introduce systems belonging to a particular category predominantly compare them with other systems within the same category, offering limited or no comparison with systems from the other category. Some prior work also justifies its focus on one specific training method by arguing that it achieves higher accuracy than the alternative. The literature, however, has incomplete and contradictory evidence in this regard. In this paper, we provide a comprehensive empirical comparison of representative full-graph and mini-batch GNN training systems. We find that the mini-batch training systems consistently converge faster than the full-graph training ones across multiple datasets, GNN models, and system configurations. We also find that mini-batch training techniques converge to similar to or often higher accuracy values than full-graph training ones, showing that mini-batch sampling is not necessarily detrimental to accuracy. Our work highlights the importance of comparing systems across different classes, using time-to-accuracy rather than epoch time for performance comparison, and selecting appropriate hyperparameters for each training method separately.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑