软置换:学习图表示的软置换
Permute Me Softly: Learning Soft Permutations for Graph Representations
摘要:
图神经网络(GNN)最近已经成为利用图进行机器学习的主导范例。对GNN的研究主要集中在消息传递神经网络(MPNN)家族上。类似于同构的Weisfeiler-Leman(WL)测试,这些模型遵循迭代邻域聚合过程来更新顶点表示,然后通过聚合顶点的表示来计算图形表示。虽然非常成功,MPNN在过去几年中得到了深入的研究。因此,需要一种新的架构,这将使该领域的研究脱离MPNN。在本文中,我们提出了一种新的图神经网络模型,即所谓的$π$ -GNN,它学习“软”排列(即,双随机)矩阵,从而将所有图投影到公共向量空间中。学习的矩阵对输入图的顶点施加“软”排序,并且基于该排序,邻接矩阵被映射到向量。这些向量可以被馈送到全连接或卷积层中,以处理监督学习任务。在大型图的情况下,为了使模型在运行时间和内存方面更有效,我们进一步将双随机阵放宽到行随机阵。我们在图分类和图回归数据集上对该模型进行了经验评估,结果表明,该模型的性能与最先进的模型相比具有竞争力。
英文摘要:
Graph neural networks (GNNs) have recently emerged as a dominant paradigm for machine learning with graphs. Research on GNNs has mainly focused on the family of message passing neural networks (MPNNs). Similar to the Weisfeiler-Leman (WL) test of isomorphism, these models follow an iterative neighborhood aggregation procedure to update vertex representations, and they next compute graph representations by aggregating the representations of the vertices. Although very successful, MPNNs have been studied intensively in the past few years. Thus, there is a need for novel architectures which will allow research in the field to break away from MPNNs. In this paper, we propose a new graph neural network model, so-called $π$-GNN which learns a "soft" permutation (i.e., doubly stochastic) matrix for each graph, and thus projects all graphs into a common vector space. The learned matrices impose a "soft" ordering on the vertices of the input graphs, and based on this ordering, the adjacency matrices are mapped into vectors. These vectors can be fed into fully-connected or convolutional layers to deal with supervised learning tasks. In case of large graphs, to make the model more efficient in terms of running time and memory, we further relax the doubly stochastic matrices to row stochastic matrices. We empirically evaluate the model on graph classification and graph regression datasets and show that it achieves performance competitive with state-of-the-art models.
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。