arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14883cs.LG
收藏

TGL:一个基于十亿级图的时间GNN训练的通用框架

TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs

University of Southern California(南加州大学);AWS AI(亚马逊云科技人工智能部门)

Hongkuan Zhou, Da Zheng, Israt Nisa, Vasileios Ioannidis, Xiang Song, George Karypis

摘要:

许多真实世界的图形包含时域信息。时间图神经网络在生成的动态节点嵌入中捕获时间信息以及结构和上下文信息。研究人员已经证明,这些嵌入在许多不同的任务中实现了最先进的性能。在这项工作中,我们提出了TGL,一个统一的框架,用于大规模离线时间图神经网络训练,用户可以组成各种时间图神经网络与简单的配置文件。TGL包括五个主要组件:时间采样器、邮箱、节点内存模块、内存更新器和消息传递引擎。我们设计了一个Temporal-CSR数据结构和一个并行采样器来有效地采样时间邻居以形成训练小批量。我们提出了一种新的随机块调度技术,减轻了过时的节点内存的问题时,训练大批量。为了解决当前TGNN仅在小规模数据集上进行评估的局限性,我们引入了两个具有2亿和13亿时间边缘的大规模真实世界数据集。我们评估的性能TGL四个小规模的数据集与一个单一的GPU和两个大的数据集与多个GPU的链接预测和节点分类任务。我们将TGL与五种方法的开源代码进行了比较,结果表明TGL实现了相似或更好的准确性,平均加速13倍。与基线相比,我们的时间并行采样器在多核CPU上实现了平均173倍的加速比。在4-GPU机器上,TGL可以在1-10小时内训练超过10亿条时间边的一个epoch。据我们所知,这是第一个提出在多个GPU上进行大规模时间图神经网络训练的通用框架的工作。

英文摘要:

Many real world graphs contain time domain information. Temporal Graph Neural Networks capture temporal information as well as structural and contextual information in the generated dynamic node embeddings. Researchers have shown that these embeddings achieve state-of-the-art performance in many different tasks. In this work, we propose TGL, a unified framework for large-scale offline Temporal Graph Neural Network training where users can compose various Temporal Graph Neural Networks with simple configuration files. TGL comprises five main components, a temporal sampler, a mailbox, a node memory module, a memory updater, and a message passing engine. We design a Temporal-CSR data structure and a parallel sampler to efficiently sample temporal neighbors to formtraining mini-batches. We propose a novel random chunk scheduling technique that mitigates the problem of obsolete node memory when training with a large batch size. To address the limitations of current TGNNs only being evaluated on small-scale datasets, we introduce two large-scale real-world datasets with 0.2 and 1.3 billion temporal edges. We evaluate the performance of TGL on four small-scale datasets with a single GPU and the two large datasets with multiple GPUs for both link prediction and node classification tasks. We compare TGL with the open-sourced code of five methods and show that TGL achieves similar or better accuracy with an average of 13x speedup. Our temporal parallel sampler achieves an average of 173x speedup on a multi-core CPU compared with the baselines. On a 4-GPU machine, TGL can train one epoch of more than one billion temporal edges within 1-10 hours. To the best of our knowledge, this is the first work that proposes a general framework for large-scale Temporal Graph Neural Networks training on multiple GPUs.

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。

↑