arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.03546cs.LG
收藏

基于强化学习和图神经网络的图划分和稀疏矩阵排序

Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks

Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);University of California, Santa Cruz(加州大学圣克鲁兹分校)

Alice Gatti, Zhixiong Hu, Tess Smidt, Esmond G. Ng, Pieter Ghysels

摘要:

提出了一种基于强化学习和图卷积神经网络的图划分新方法。我们的方法是递归分区粗糙表示一个给定的图。神经网络使用SAGE图卷积层来实现,并使用优势演员评论家(A2C)代理来训练。我们提出了两个变体,一个用于找到最小化归一化切割或商切割的边缘分隔符,另一个用于找到小的顶点分隔符。顶点分隔符然后被用来构造一个嵌套的解剖排序置换稀疏矩阵,使其三角分解将招致更少的填充。分区质量进行了比较,使用METIS和SCOTCH获得的分区,并在稀疏求解器SuperLU的嵌套解剖排序进行评估。我们的研究结果表明,该方法实现了类似的分割质量METIS和SCOTCH。此外,该方法可以推广到不同类别的图,并且可以很好地处理SuiteSparse稀疏矩阵集合中的各种图。

英文摘要:

We present a novel method for graph partitioning, based on reinforcement learning and graph convolutional neural networks. Our approach is to recursively partition coarser representations of a given graph. The neural network is implemented using SAGE graph convolution layers, and trained using an advantage actor critic (A2C) agent. We present two variants, one for finding an edge separator that minimizes the normalized cut or quotient cut, and one that finds a small vertex separator. The vertex separators are then used to construct a nested dissection ordering to permute a sparse matrix so that its triangular factorization will incur less fill-in. The partitioning quality is compared with partitions obtained using METIS and SCOTCH, and the nested dissection ordering is evaluated in the sparse solver SuperLU. Our results show that the proposed method achieves similar partitioning quality as METIS and SCOTCH. Furthermore, the method generalizes across different classes of graphs, and works well on a variety of graphs from the SuiteSparse sparse matrix collection.

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。

↑