arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09422cs.LGcs.AIcs.SIstat.ML
收藏

大规模图表示学习与非常深的GNN和自我监督

Large-scale graph representation learning with very deep GNNs and self-supervision

DeepMind(深度思维);Mila(米拉研究所);Université de Montréal(蒙特利尔大学)
Ravichandra Addanki, Peter W. Battaglia, David Budden, Andreea Deac, Jonathan Godwin, Thomas Keck, Wai Lok Sibon Li, Alvaro Sanchez-Gonzalez, Jacklynn Stott, Sh… 展开作者

Ravichandra Addanki, Peter W. Battaglia, David Budden, Andreea Deac, Jonathan Godwin, Thomas Keck, Wai Lok Sibon Li, Alvaro Sanchez-Gonzalez, Jacklynn Stott, Shantanu Thakoor, Petar Veličković

摘要:

有效和高效地大规模部署图神经网络(GNN)仍然是图表示学习最具挑战性的方面之一。许多强大的解决方案只在相对较小的数据集上进行过验证,通常会产生违反直觉的结果-这一障碍已被开放图基准大规模挑战赛(OGB-LSC)打破。我们使用两个大规模GNN进入OGB-LSC:一个由自举驱动的深度转导节点分类器,以及一个由去噪目标正则化的非常深(高达50层)的归纳图回归器。我们的模型在MAG 240 M和PCQM 4 M基准测试中均获得了获奖级别(前3名)的性能。在这样做的过程中,我们展示了可扩展的自监督图表示学习的证据,以及非常深的GNN的实用性-这两个都是非常重要的开放问题。我们的代码可在https://github.com/deepmind/deepmind-research/tree/master/ogb_lsc上公开获取。

英文摘要:

Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of the most challenging aspects of graph representation learning. Many powerful solutions have only ever been validated on comparatively small datasets, often with counter-intuitive outcomes -- a barrier which has been broken by the Open Graph Benchmark Large-Scale Challenge (OGB-LSC). We entered the OGB-LSC with two large-scale GNNs: a deep transductive node classifier powered by bootstrapping, and a very deep (up to 50-layer) inductive graph regressor regularised by denoising objectives. Our models achieved an award-level (top-3) performance on both the MAG240M and PCQM4M benchmarks. In doing so, we demonstrate evidence of scalable self-supervised graph representation learning, and utility of very deep GNNs -- both very important open issues. Our code is publicly available at: https://github.com/deepmind/deepmind-research/tree/master/ogb_lsc.

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。

↑