arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15097cs.LGstat.ML
收藏

Policy-GNN:图神经网络的聚集优化

Policy-GNN: Aggregation Optimization for Graph Neural Networks

Texas A&M University(德州农工大学)

Kwei-Herng Lai, Daochen Zha, Kaixiong Zhou, Xia Hu

摘要:

图数据在许多现实世界的应用中是普遍存在的。近年来,图神经网络(graph neural networks,GNNs)越来越受到人们的关注。GNNs的目标是通过利用可堆叠的网络模块聚集来自邻居的信息来建模局部图结构并捕获层次模式。由于观察到不同的节点通常需要不同的聚合迭代才能完全捕获结构信息,因此在本文中,我们建议对不同节点的聚合迭代进行显式采样,以提高GNN的性能。这是一个具有挑战性的任务,制定一个有效的聚合策略,为每个节点,给定的复杂的图形和稀疏的功能。此外,由于我们需要将采样节点馈送到不同数量的网络层中,因此推导出有效的算法并不简单。为了解决上述挑战,我们提出了Policy-GNN,这是一个元策略框架,它将GNN的采样过程和消息传递建模为组合学习过程。具体来说,Policy-GNN使用元策略来自适应地确定每个节点的聚合数量。通过利用来自模型的反馈,使用深度强化学习(RL)来训练元策略。我们进一步引入参数共享和缓冲机制来提高训练效率。在三个真实世界基准数据集上的实验结果表明,Policy-GNN显著优于最先进的替代方案,显示了GNN聚合优化的前景。

英文摘要:

Graph data are pervasive in many real-world applications. Recently, increasing attention has been paid on graph neural networks (GNNs), which aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors with stackable network modules. Motivated by the observation that different nodes often require different iterations of aggregation to fully capture the structural information, in this paper, we propose to explicitly sample diverse iterations of aggregation for different nodes to boost the performance of GNNs. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. Moreover, it is not straightforward to derive an efficient algorithm since we need to feed the sampled nodes into different number of network layers. To address the above challenges, we propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process. Specifically, Policy-GNN uses a meta-policy to adaptively determine the number of aggregations for each node. The meta-policy is trained with deep reinforcement learning (RL) by exploiting the feedback from the model. We further introduce parameter sharing and a buffer mechanism to boost the training efficiency. Experimental results on three real-world benchmark datasets suggest that Policy-GNN significantly outperforms the state-of-the-art alternatives, showing the promise in aggregation optimization for GNNs.

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。

↑