图形神经网络（GNNS）使用图形卷积来利用网络不向导并从网络数据中学习有意义的特征表示。但是，在大规模图中，卷积以高计算成本产生，导致可伸缩性限制。在本文中，我们考虑了学习图形神经网络（WNN）的问题 - GNN的极限对象 - 通过训练从Graphon采样的图形上，我们考虑了学习GragraN神经网络（WNN）的问题。在平滑性条件下，我们表明：（i）GNN和WNN上的学习步骤之间的预期距离随图形的尺寸渐近地降低，并且（ii）在一系列生长图上训练时，梯度下降遵循WNN的学习方向。受这些结果的启发，我们提出了一种新型算法，以学习大规模图的GNN，从中等数量的节点开始，在训练过程中依次增加了图的大小。该算法是在分散的控制问题上进一步基准的，在该问题下，它以降低的计算成本保留了与大规模对应物相当的性能。

图形神经网络（GNNS）是由图形卷积和叉指非线性组成的层组成的深度卷积架构。由于其不变性和稳定性属性，GNN在网络数据的学习陈述中被证明是成功的。但是，训练它们需要矩阵计算，这对于大图可能是昂贵的。为了解决这个限制，我们研究了GNN横跨图形转移的能力。我们考虑图形，这是加权和随机图形的图形限制和生成模型，以定义图形卷积和GNNS - Graphon卷曲和Graphon神经网络（WNNS）的限制对象 - 我们用作图形卷曲的生成模型和GNNS。我们表明，这些石墨源区和WNN可以通过图形滤波器和来自加权和随机图中的它们采样的GNN来近似。使用这些结果，我们将导出误差界限，用于跨越此类图形传输图形过滤器和GNN。这些界限表明，可转换性随着图尺寸的增加而增加，并且揭示了在GNN中的可转换性和光谱分辨率之间的折衷，其被点亮的非线性缓解。这些发现经验在电影推荐和分散机器人控制中的数值实验中进行了经验验证。

我们研究光谱图卷积神经网络（GCNN），其中过滤器被定义为通过功能计算的图形移位算子（GSO）的连续函数。光谱GCNN不是针对一个特定图的量身定制的，可以在不同的图之间传输。因此，研究GCNN的可传递性很重要：网络在代表相同现象的不同图上具有大致相同影响的能力。如果测试集中的图与训练集中的图形相同，则可传递性可确保在某些图上进行训练的GCNN概括。在本文中，我们考虑了基于Graphon分析的可转让性模型。图形是图形的极限对象，在图形范式中，如果两者都近似相同的图形，则两个图表示相同的现象。我们的主要贡献可以总结如下：1）我们证明，在近似于同一图形的图的图下，任何具有连续过滤器的固定GCNN都是可以转移的，2）我们证明了近似于未结合的图形换档运算符的图形，该图是在本文中定义的，和3）我们获得了非反应近似结果，证明了GCNN的线性稳定性。这扩展了当前的最新结果，这些结果显示了在近似界图子的图下显示多项式过滤器的渐近可传递性。

We introduce an architecture for processing signals supported on hypergraphs via graph neural networks (GNNs), which we call a Hyper-graph Expansion Neural Network (HENN), and provide the first bounds on the stability and transferability error of a hypergraph signal processing model. To do so, we provide a framework for bounding the stability and transferability error of GNNs across arbitrary graphs via spectral similarity. By bounding the difference between two graph shift operators (GSOs) in the positive semi-definite sense via their eigenvalue spectrum, we show that this error depends only on the properties of the GNN and the magnitude of spectral similarity of the GSOs. Moreover, we show that existing transferability results that assume the graphs are small perturbations of one another, or that the graphs are random and drawn from the same distribution or sampled from the same graphon can be recovered using our approach. Thus, both GNNs and our HENNs (trained using normalized Laplacians as graph shift operators) will be increasingly stable and transferable as the graphs become larger. Experimental results illustrate the importance of considering multiple graph representations in HENN, and show its superior performance when transferability is desired.

Although theoretical properties such as expressive power and over-smoothing of graph neural networks (GNN) have been extensively studied recently, its convergence property is a relatively new direction. In this paper, we investigate the convergence of one powerful GNN, Invariant Graph Network (IGN) over graphs sampled from graphons. We first prove the stability of linear layers for general $k$-IGN (of order $k$) based on a novel interpretation of linear equivariant layers. Building upon this result, we prove the convergence of $k$-IGN under the model of \citet{ruiz2020graphon}, where we access the edge weight but the convergence error is measured for graphon inputs. Under the more natural (and more challenging) setting of \citet{keriven2020convergence} where one can only access 0-1 adjacency matrix sampled according to edge probability, we first show a negative result that the convergence of any IGN is not possible. We then obtain the convergence of a subset of IGNs, denoted as IGN-small, after the edge probability estimation. We show that IGN-small still contains function class rich enough that can approximate spectral GNNs arbitrarily well. Lastly, we perform experiments on various graphon models to verify our statements.

In this paper we propose a pooling approach for convolutional information processing on graphs relying on the theory of graphons and limits of dense graph sequences. We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1]2 in the graphon space. As a result we derive low dimensional representations of the convolutional operators, while a dimensionality reduction of the signals is achieved by simple local interpolation of functions in L2([0, 1]). We prove that those low dimensional representations constitute a convergent sequence of graphs and graph signals, respectively. The methods proposed and the theoretical guarantees that we provide show that the reduced graphs and signals inherit spectral-structural properties of the original quantities. We evaluate our approach with a set of numerical experiments performed on graph neural networks (GNNs) that rely on graphon pooling. We observe that graphon pooling performs significantly better than other approaches proposed in the literature when dimensionality reduction ratios between layers are large. We also observe that when graphon pooling is used we have, in general, less overfitting and lower computational cost.

图表神经网络（GNNS）最近已经证明了在各种基于网络的任务中表现出良好的基于​​网络的任务，例如分散控制和资源分配，并为这些任务提供传统上在这方面挑战的计算有效方法。然而，与许多基于神经网络的系统一样，GNN易于在其输入上移动和扰动，其可以包括节点属性和图形结构。为了使它们更有用的真实应用程序，重要的是确保其稳健性后部署。通过控制GNN滤波器的LIPSChitz常数相对于节点属性来激励，我们建议约束GNN过滤器组的频率响应。我们使用连续频率响应约束将该配方扩展到动态图形设置，并通过方案方法解决问题的轻松变体。这允许在采样约束上使用相同的计算上有效的算法，这为PAC-Sique提供了在GNN的稳定性上使用方案优化的结果提供了PAC样式的保证。我们还突出了该设置和GNN稳定性与图形扰动之间的重要联系，并提供了实验结果，证明了我们方法的功效和宽广。

随机图神经网络（SGNN）是信息处理体系结构，可从随机图中学习表示表示。 SGNN受到预期性能的培训，这不能保证围绕最佳期望的特定输出实现的偏差。为了克服这个问题，我们为SGNN提出了一个方差约束优化问题，平衡了预期的性能和随机偏差。通过使用梯度下降和梯度上升的双变量更新SGNN参数，进行了交替的原始双偶学习过程，该过程通过更新SGNN参数来解决问题。为了表征方差约束学习的明确效应，我们对SGNN输出方差进行理论分析，并确定随机鲁棒性和歧视能力之间的权衡。我们进一步分析了方差约束优化问题的二元性差距以及原始双重学习过程的融合行为。前者表示双重变换引起的最优性损失，后者是迭代算法的限制误差，这两者都保证了方差约束学习的性能。通过数值模拟，我们证实了我们的理论发现，并观察到具有可控标准偏差的强劲预期性能。

Spectral methods provide consistent estimators for community detection in dense graphs. However, their performance deteriorates as the graphs become sparser. In this work we consider a random graph model that can produce graphs at different levels of sparsity, and we show that graph neural networks can outperform spectral methods on sparse graphs. We illustrate the results with numerical examples in both synthetic and real graphs.

Network data are ubiquitous in modern machine learning, with tasks of interest including node classification, node clustering and link prediction. A frequent approach begins by learning an Euclidean embedding of the network, to which algorithms developed for vector-valued data are applied. For large networks, embeddings are learned using stochastic gradient methods where the sub-sampling scheme can be freely chosen. Despite the strong empirical performance of such methods, they are not well understood theoretically. Our work encapsulates representation methods using a subsampling approach, such as node2vec, into a single unifying framework. We prove, under the assumption that the graph is exchangeable, that the distribution of the learned embedding vectors asymptotically decouples. Moreover, we characterize the asymptotic distribution and provided rates of convergence, in terms of the latent parameters, which includes the choice of loss function and the embedding dimension. This provides a theoretical foundation to understand what the embedding vectors represent and how well these methods perform on downstream tasks. Notably, we observe that typically used loss functions may lead to shortcomings, such as a lack of Fisher consistency.

消息传递神经网络（MPNN）自从引入卷积神经网络以泛滥到图形结构的数据以来，人们的受欢迎程度急剧上升，现在被认为是解决各种以图形为中心的最先进的工具问题。我们研究图形分类和回归中MPNN的概括误差。我们假设不同类别的图是从不同的随机图模型中采样的。我们表明，当在从这种分布中采样的数据集上训练MPNN时，概括差距会增加MPNN的复杂性，并且不仅相对于训练样本的数量，而且还会减少节点的平均数量在图中。这表明，只要图形很大，具有高复杂性的MPNN如何从图形的小数据集中概括。概括结合是从均匀收敛结果得出的，该结果表明，应用于图的任何MPNN近似于该图离散的几何模型上应用的MPNN。

Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) their predictive performance as we pile up many layers and add non-lineality. To tackle this problem, we investigate the expressive power of graph NNs via their asymptotic behaviors as the layer size tends to infinity. Our strategy is to generalize the forward propagation of a Graph Convolutional Network (GCN), which is a popular graph NN variant, as a specific dynamical system. In the case of a GCN, we show that when its weights satisfy the conditions determined by the spectra of the (augmented) normalized Laplacian, its output exponentially approaches the set of signals that carry information of the connected components and node degrees only for distinguishing nodes. Our theory enables us to relate the expressive power of GCNs with the topological information of the underlying graphs inherent in the graph spectra. To demonstrate this, we characterize the asymptotic behavior of GCNs on the Erdős -Rényi graph. We show that when the Erdős -Rényi graph is sufficiently dense and large, a broad range of GCNs on it suffers from the "information loss" in the limit of infinite layers with high probability. Based on the theory, we provide a principled guideline for weight normalization of graph NNs. We experimentally confirm that the proposed weight scaling enhances the predictive performance of GCNs in real data 1 .

分散和联合学习的关键挑战之一是设计算法，这些算法有效地处理跨代理商的高度异构数据分布。在本文中，我们在数据异质性下重新审视分散的随机梯度下降算法（D-SGD）的分析。我们在D-SGD的收敛速率上展示了新数量的关键作用，称为\ emph {邻居异质性}。通过结合通信拓扑结构和异质性，我们的分析阐明了这两个分散学习中这两个概念之间的相互作用较低。然后，我们认为邻里的异质性提供了一种自然标准，可以学习数据依赖性拓扑结构，以减少（甚至可以消除）数据异质性对D-SGD收敛时间的有害影响。对于与标签偏度分类的重要情况，我们制定了学习这样一个良好拓扑的问题，例如我们使用Frank-Wolfe算法解决的可拖动优化问题。如一组模拟和现实世界实验所示，我们的方法提供了一种设计稀疏拓扑的方法，可以在数据异质性下平衡D-SGD的收敛速度和D-SGD的触电沟通成本。

Artificial neural networks are functions depending on a finite number of parameters typically encoded as weights and biases. The identification of the parameters of the network from finite samples of input-output pairs is often referred to as the \emph{teacher-student model}, and this model has represented a popular framework for understanding training and generalization. Even if the problem is NP-complete in the worst case, a rapidly growing literature -- after adding suitable distributional assumptions -- has established finite sample identification of two-layer networks with a number of neurons $m=\mathcal O(D)$, $D$ being the input dimension. For the range $D<m<D^2$ the problem becomes harder, and truly little is known for networks parametrized by biases as well. This paper fills the gap by providing constructive methods and theoretical guarantees of finite sample identification for such wider shallow networks with biases. Our approach is based on a two-step pipeline: first, we recover the direction of the weights, by exploiting second order information; next, we identify the signs by suitable algebraic evaluations, and we recover the biases by empirical risk minimization via gradient descent. Numerical results demonstrate the effectiveness of our approach.

在本文中，我们研究了考虑基础图的扰动的聚集图神经网络（ag-gnns）的稳定性。 Agg-gnn是一种混合体系结构，在图上定义了信息，但是在图形移位算子上进行了几次扩散后，在节点上的欧几里得CNN对其进行了处理。我们为与通用Agg-GNN关联的映射运算符得出稳定性界限，并指定了该操作员可以稳定变形的条件。我们证明稳定性边界是由在每个节点上作用的CNN的第一层中过滤器的属性定义的。此外，我们表明聚集的数量，滤波器的选择性和稳定性常数的大小之间存在密切的关系。我们还得出结论，在Agg-gnns中，映射运算符的选择性仅在CNN阶段的第一层中与过滤器的属性相关。这显示了相对于选择GNN的稳定性的实质性差异，其中所有层中过滤器的选择性受其稳定性的约束。我们提供了证实结果得出的结果的数值证据，测试了考虑不同幅度扰动的现实生活应用方案中的ag-gnn的行为。

Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to log nfactors) under a general composition assumption on the regression function. The framework includes many well-studied structural constraints such as (generalized) additive models. While there is a lot of flexibility in the network architecture, the tuning parameter is the sparsity of the network. Specifically, we consider large networks with number of potential network parameters exceeding the sample size. The analysis gives some insights into why multilayer feedforward neural networks perform well in practice. Interestingly, for ReLU activation function the depth (number of layers) of the neural network architectures plays an important role and our theory suggests that for nonparametric regression, scaling the network depth with the sample size is natural. It is also shown that under the composition assumption wavelet estimators can only achieve suboptimal rates.

我们为特殊神经网络架构，称为运营商复发性神经网络的理论分析，用于近似非线性函数，其输入是线性运算符。这些功能通常在解决方案算法中出现用于逆边值问题的问题。传统的神经网络将输入数据视为向量，因此它们没有有效地捕获与对应于这种逆问题中的数据的线性运算符相关联的乘法结构。因此，我们介绍一个类似标准的神经网络架构的新系列，但是输入数据在向量上乘法作用。由较小的算子出现在边界控制中的紧凑型操作员和波动方程的反边值问题分析，我们在网络中的选择权重矩阵中促进结构和稀疏性。在描述此架构后，我们研究其表示属性以及其近似属性。我们还表明，可以引入明确的正则化，其可以从所述逆问题的数学分析导出，并导致概括属性上的某些保证。我们观察到重量矩阵的稀疏性改善了概括估计。最后，我们讨论如何将运营商复发网络视为深度学习模拟，以确定诸如用于从边界测量的声波方程中重建所未知的WAVESTED的边界控制的算法算法。

在深度学习中的优化分析是连续的，专注于（变体）梯度流动，或离散，直接处理（变体）梯度下降。梯度流程可符合理论分析，但是风格化并忽略计算效率。它代表梯度下降的程度是深度学习理论的一个开放问题。目前的论文研究了这个问题。将梯度下降视为梯度流量初始值问题的近似数值问题，发现近似程度取决于梯度流动轨迹周围的曲率。然后，我们表明，在具有均匀激活的深度神经网络中，梯度流动轨迹享有有利的曲率，表明它们通过梯度下降近似地近似。该发现允许我们将深度线性神经网络的梯度流分析转换为保证梯度下降，其几乎肯定会在随机初始化下有效地收敛到全局最小值。实验表明，在简单的深度神经网络中，具有传统步长的梯度下降确实接近梯度流。我们假设梯度流动理论将解开深入学习背后的奥秘。

过度参数化神经网络（NNS）的小概括误差可以通过频率偏见现象来部分解释，在频率偏置现象中，基于梯度的算法将低频失误最小化，然后再减少高频残差。使用神经切线内核（NTK），可以为训练提供理论上严格的分析，其中数据是从恒定或分段构剂概率密度绘制的数据。由于大多数训练数据集不是从此类分布中汲取的，因此我们使用NTK模型和数据依赖性的正交规则来理论上量化NN训练的频率偏差，给定完全不均匀的数据。通过用精心选择的Sobolev规范替换损失函数，我们可以进一步扩大，抑制，平衡或逆转NN训练中的内在频率偏差。

散射变换是一种基于多层的小波的深度学习架构，其充当卷积神经网络的模型。最近，几种作品引入了非欧几里德设置的散射变换的概括，例如图形。我们的工作通过基于非常一般的非对称小波来引入图形的窗口和非窗口几何散射变换来构建这些结构。我们表明，这些不对称的图形散射变换具有许多与其对称对应的相同的理论保证。结果，所提出的结构统一并扩展了许多现有图散射架构的已知理论结果。在这样做时，这项工作有助于通过引入具有可提供稳定性和不变性保证的大型网络，帮助弥合几何散射和其他图形神经网络之间的差距。这些结果为未来的图形结构数据奠定了基础，对具有学习过滤器的图形结构数据，并且还可以证明具有理想的理论特性。