arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.06376cs.LGstat.ML
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 Networks with Distributed Online Learning

University of Pennsylvania(宾夕法尼亚大学);University of California, Berkeley(加州大学伯克利分校)

Zhan Gao, Fernando Gama, Alejandro Ribeiro

摘要:

图神经网络(GNN)从具有自然分布式架构的网络数据中学习表示,使其非常适合分散式学习。通常情况下,这种分散的图支持由于链路故障或拓扑变化而随时间变化。这些变化在GNN训练的图形和测试的图形之间造成了不匹配。在线学习可用于在测试时重新训练GNN,从而克服这个问题。然而,大多数在线算法都是集中式的,并且处理凸问题(GNN很少导致凸问题)。本文提出了宽和深GNN(WD-GNN),一种新的架构,可以很容易地更新与分布式在线学习机制。WD-GNN由两部分组成:宽部分是一组线性图滤波器,深部分是GNN。在训练时,联合架构从数据中学习非线性表示。在测试时,深度部分(非线性)保持不变,而宽部分在线重新训练,导致凸问题。我们得到收敛保证这个在线再培训过程,并进一步提出了一个分散的替代方案。群集机器人群体控制的实验证实了理论和分布式在线学习的建议架构的潜力。

英文摘要:

Graph neural networks (GNNs) learn representations from network data with naturally distributed architectures, rendering them well-suited candidates for decentralized learning. Oftentimes, this decentralized graph support changes with time due to link failures or topology variations. These changes create a mismatch between the graphs on which GNNs were trained and the ones on which they are tested. Online learning can be used to retrain GNNs at testing time, overcoming this issue. However, most online algorithms are centralized and work on convex problems (which GNNs rarely lead to). This paper proposes the Wide and Deep GNN (WD-GNN), a novel architecture that can be easily updated with distributed online learning mechanisms. The WD-GNN comprises two components: the wide part is a bank of linear graph filters and the deep part is a GNN. At training time, the joint architecture learns a nonlinear representation from data. At testing time, the deep part (nonlinear) is left unchanged, while the wide part is retrained online, leading to a convex problem. We derive convergence guarantees for this online retraining procedure and further propose a decentralized alternative. Experiments on the robot swarm control for flocking corroborate theory and show potential of the proposed architecture 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。

↑