FedGraph: Federated Graph Learning With Intelligent Sampling
FedGraph: Federated Graph Learning With Intelligent Sampling
复制标题
DOI：
10.1109/tpds.2021.3125565
复制
发表时间：
2021-11
影响因子：
5.3
通讯作者：
Fahao Chen;Peng Li;T. Miyazaki;Celimuge Wu
中科院分区：
文献类型：
--
作者：
Fahao Chen;Peng Li;T. Miyazaki;Celimuge Wu
联邦学习因其在分布式机器学习中的隐私保护而引起了广泛的研究关注。然而，联邦学习的现有工作主要集中在卷积神经网络（CNN）上，它不能有效地处理在许多应用中流行的图数据。图卷积网络（GCN）被认为是最有前途的图学习技术之一，但其联邦设置很少被探索。在本文中，我们提出 FedGraph 用于多个计算客户端之间的联合图学习，每个客户端都拥有一个子图。 FedGraph 通过解决两个独特的挑战，为客户提供强大的图形学习能力。首先，传统的GCN训练需要客户端之间共享特征数据，存在隐私泄露的风险。 FedGraph 使用一种新颖的跨客户端卷积运算解决了这个问题。第二个挑战是大图尺寸带来的高 GCN 训练开销。我们提出了一种基于深度强化学习的智能图采样算法，该算法可以自动收敛到平衡训练速度和准确性的最优采样策略。我们基于 PyTorch 实现 FedGraph 并将其部署在测试床上进行性能评估。四个流行数据集的实验结果表明，FedGraph 通过实现更快的收敛速度和更高的精度，显着优于现有的工作。
Federated learning has attracted much research attention due to its privacy protection in distributed machine learning. However, existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), which cannot efficiently handle graph data that are popular in many applications. Graph Convolutional Network (GCN) has been proposed as one of the most promising techniques for graph learning, but its federated setting has been seldom explored. In this article, we propose FedGraph for federated graph learning among multiple computing clients, each of which holds a subgraph. FedGraph provides strong graph learning capability across clients by addressing two unique challenges. First, traditional GCN training needs feature data sharing among clients, leading to risk of privacy leakage. FedGraph solves this issue using a novel cross-client convolution operation. The second challenge is high GCN training overhead incurred by large graph size. We propose an intelligent graph sampling algorithm based on deep reinforcement learning, which can automatically converge to the optimal sampling policies that balance training speed and accuracy. We implement FedGraph based on PyTorch and deploy it on a testbed for performance evaluation. The experimental results of four popular datasets demonstrate that FedGraph significantly outperforms existing work by enabling faster convergence to higher accuracy.