arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.11577cs.LGcs.AIstat.ML
收藏

从数据流形学习依赖可分图卷积

Learning Depthwise Separable Graph Convolution from Data Manifold

Carnegie Mellon University(卡内基梅隆大学)

Guokun Lai, Hanxiao Liu, Yiming Yang

摘要:

卷积神经网络(CNN)以其出色的局部特征捕捉能力在计算机视觉领域取得了巨大的成功。近年来,将卷积运算扩展到非欧几何中的研究越来越受到人们的关注。尽管已经为图或流形提出了各种类型的卷积运算,但它们与网格结构数据上的传统卷积的联系还没有得到很好的理解。在本文中,我们表明,dependency可分离卷积可以成功地推广为统一的基于图形和基于网格的卷积方法。基于这一认识,我们提出了一种新的依赖可分离图卷积(DSGC)方法,它与传统的卷积网络兼容,并将现有的卷积方法作为特例。它具有模型表达能力,兼容性(参数数量相对较少),模块化和训练计算效率的综合优势。大量的实验表明,DSGC在多域基准数据集上与强基线相比具有出色的性能。

英文摘要:

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations have been proposed for graphs or manifolds, their connections with traditional convolution over grid-structured data are not well-understood. In this paper, we show that depthwise separable convolution can be successfully generalized for the unification of both graph-based and grid-based convolution methods. Based on this insight we propose a novel Depthwise Separable Graph Convolution (DSGC) approach which is compatible with the tradition convolution network and subsumes existing convolution methods as special cases. It is equipped with the combined strengths in model expressiveness, compatibility (relatively small number of parameters), modularity and computational efficiency in training. Extensive experiments show the outstanding performance of DSGC in comparison with strong baselines on multi-domain benchmark datasets.

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。

↑