arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06555cs.LG
收藏

在线图字典学习

Online Graph Dictionary Learning

Univ.Côte d’Azur(蔚蓝海岸大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);ENS de Lyon(里昂高等师范学院);Ecole Polytechnique(巴黎综合理工学院);IRISA(布列塔尼大西洋信息技术与系统研究所)

Cédric Vincent-Cuaz, Titouan Vayer, Rémi Flamary, Marco Corneli, Nicolas Courty

摘要:

字典学习是表示学习的一个重要工具,它将数据解释为几个基本元素的线性组合。然而,这种分析在图学习的背景下不适用,因为图通常属于不同的度量空间。我们通过提出一种新的在线图字典学习方法来填补这一空白,该方法使用Gromov Wasserstein分歧作为数据拟合项。在我们的工作中,图通过其节点的成对关系进行编码,并建模为图原子的凸组合,即字典元素,通过在线随机算法进行估计,该算法在具有潜在不同节点数的未注册图的数据集上进行操作。我们的方法自然地扩展到标记图,并完成了一个新的上限,可以作为一个快速近似的Gromov Wasserstein在嵌入空间。我们提供的数字证据表明,我们的方法的兴趣,无监督嵌入的图形数据集和在线图子空间估计和跟踪。

英文摘要:

Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements. Yet, this analysis is not amenable in the context of graph learning, as graphs usually belong to different metric spaces. We fill this gap by proposing a new online Graph Dictionary Learning approach, which uses the Gromov Wasserstein divergence for the data fitting term. In our work, graphs are encoded through their nodes' pairwise relations and modeled as convex combination of graph atoms, i.e. dictionary elements, estimated thanks to an online stochastic algorithm, which operates on a dataset of unregistered graphs with potentially different number of nodes. Our approach naturally extends to labeled graphs, and is completed by a novel upper bound that can be used as a fast approximation of Gromov Wasserstein in the embedding space. We provide numerical evidences showing the interest of our approach for unsupervised embedding of graph datasets and for online graph subspace estimation and tracking.

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。

↑