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 2107.09203cs.LGeess.SP
收藏

具有分布式在线学习的宽深度图神经网络

Wide and Deep Graph Neural Network with Distributed Online Learning

Univ. of Pennsylvania(宾夕法尼亚大学);Rice Univ.(莱斯大学)

Zhan Gao, Fernando Gama, Alejandro Ribeiro

摘要:

图神经网络(GNN)是用于从网络数据学习表示的自然分布式架构。这使他们成为分散任务的合适人选。在这些场景中,由于链路故障或拓扑变化,底层图通常会随着时间而变化,从而在GNN训练的图和测试的图之间产生不匹配。可以利用在线学习在测试时重新训练GNN来克服这个问题。然而,大多数在线算法都是集中式的,通常只对凸问题提供保证,而GNN很少会导致凸问题。本文开发了宽深GNN(WD-GNN),一种新的架构,可以更新分布式在线学习机制。WD-GNN由两部分组成:宽部分是线性图滤波器,深部分是非线性GNN。在训练时,联合广度和深度架构从数据中学习非线性表示。在测试时,宽的线性部分被重新训练,而深的非线性部分保持不变。这往往导致一个凸公式。我们进一步提出了一个分布式的在线学习算法,可以在分散的设置。我们还显示了稳定的WD-GNN底层图的变化,并分析了所提出的在线学习过程的收敛性。电影推荐,源定位和机器人群体控制的实验证实了理论研究结果,并显示了分布式在线学习的WD-GNN的潜力。

英文摘要:

Graph neural networks (GNNs) are naturally distributed architectures for learning representations from network data. This renders them suitable candidates for decentralized tasks. In these scenarios, the underlying graph often changes with time due to link failures or topology variations, creating a mismatch between the graphs on which GNNs were trained and the ones on which they are tested. Online learning can be leveraged to retrain GNNs at testing time to overcome this issue. However, most online algorithms are centralized and usually offer guarantees only on convex problems, which GNNs rarely lead to. This paper develops the Wide and Deep GNN (WD-GNN), a novel architecture that can be updated with distributed online learning mechanisms. The WD-GNN consists of two components: the wide part is a linear graph filter and the deep part is a nonlinear GNN. At training time, the joint wide and deep architecture learns nonlinear representations from data. At testing time, the wide, linear part is retrained, while the deep, nonlinear one remains fixed. This often leads to a convex formulation. We further propose a distributed online learning algorithm that can be implemented in a decentralized setting. We also show the stability of the WD-GNN to changes of the underlying graph and analyze the convergence of the proposed online learning procedure. Experiments on movie recommendation, source localization and robot swarm control corroborate theoretical findings and show the potential of the WD-GNN for distributed online learning.

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。

↑