图形卷积网络(GCN)是最受欢迎的体系结构之一,用于解决分类问题,并附有图形信息。我们对图形卷积在多层网络中的影响进行了严格的理论理解。我们通过与随机块模型结合的非线性分离高斯混合模型的节点分类问题研究这些效果。首先,我们表明,单个图卷积扩展了多层网络可以至少$ 1/\ sqrt [4] {\ Mathbb {e} {\ rm veg对数据进行分类的均值之间的距离。 }} $,其中$ \ mathbb {e} {\ rm deg} $表示节点的预期度。其次,我们表明,随着图的密度稍强,两个图卷积将此因素提高到至少$ 1/\ sqrt [4] {n} $,其中$ n $是图中的节点的数量。最后,我们对网络层中不同组合的图形卷积的性能提供了理论和经验见解,得出的结论是,对于所有位置的所有组合,性能都是相互相似的。我们对合成数据和现实世界数据进行了广泛的实验,以说明我们的结果。
translated by 谷歌翻译
Graph-based learning is a rapidly growing sub-field of machine learning with applications in social networks, citation networks, and bioinformatics. One of the most popular models is graph attention networks. They were introduced to allow a node to aggregate information from features of neighbor nodes in a non-uniform way, in contrast to simple graph convolution which does not distinguish the neighbors of a node. In this paper, we study theoretically this expected behaviour of graph attention networks. We prove multiple results on the performance of graph attention mechanism for the problem of node classification for a contextual stochastic block model. Here the node features are obtained from a mixture of Gaussians and the edges from a stochastic block model. We show that in an "easy" regime, where the distance between the means of the Gaussians is large enough, graph attention is able to distinguish inter-class from intra-class edges, and thus it maintains the weights of important edges and significantly reduces the weights of unimportant edges. Consequently, we show that this implies perfect node classification. In the "hard" regime, we show that every attention mechanism fails to distinguish intra-class from inter-class edges. We evaluate our theoretical results on synthetic and real-world data.
translated by 谷歌翻译
A central challenge of building more powerful Graph Neural Networks (GNNs) is the oversmoothing phenomenon, where increasing the network depth leads to homogeneous node representations and thus worse classification performance. While previous works have only demonstrated that oversmoothing is inevitable when the number of graph convolutions tends to infinity, in this paper, we precisely characterize the mechanism behind the phenomenon via a non-asymptotic analysis. Specifically, we distinguish between two different effects when applying graph convolutions -- an undesirable mixing effect that homogenizes node representations in different classes, and a desirable denoising effect that homogenizes node representations in the same class. By quantifying these two effects on random graphs sampled from the Contextual Stochastic Block Model (CSBM), we show that oversmoothing happens once the mixing effect starts to dominate the denoising effect, and the number of layers required for this transition is $O(\log N/\log (\log N))$ for sufficiently dense graphs with $N$ nodes. We also extend our analysis to study the effects of Personalized PageRank (PPR) on oversmoothing. Our results suggest that while PPR mitigates oversmoothing at deeper layers, PPR-based architectures still achieve their best performance at a shallow depth and are outperformed by the graph convolution approach on certain graphs. Finally, we support our theoretical results with numerical experiments, which further suggest that the oversmoothing phenomenon observed in practice may be exacerbated by the difficulty of optimizing deep GNN models.
translated by 谷歌翻译
图形神经网络(GNN)在许多预测任务中表现出优于图形的优越性,因为它们在图形结构数据中捕获非线性关系的令人印象深刻。但是,对于节点分类任务,通常只观察到GNN在线性对应物上的边际改进。以前的作品对这种现象的理解很少。在这项工作中,我们求助于贝叶斯学习,以深入研究GNNS在节点分类任务中非线性的功能。鉴于从统计模型CSBM生成的图,我们观察到,给定其自身和邻居的属性的节点标签的最大a-后方估计包括两种类型的非线性,可能是节点属性和节点属性的非线性转换和来自邻居的重新激活特征聚合。后者令人惊讶地与许多GNN模型中使用的非线性类型匹配。通过进一步对节点属性施加高斯假设,我们证明,当节点属性比图形结构更具信息性时,这些relu激活的优越性才是显着的,该图与许多以前的经验观察非常匹配。当训练和测试数据集之间的节点属性分布变化时,可以实现类似的参数。最后,我们验证了关于合成和现实世界网络的理论。
translated by 谷歌翻译
尽管图形神经网络(GNNS)的巨大成功应用,但对其泛化能力的理论认识,特别是对于数据不是独立且相同分布的节点级任务(IID),稀疏。概括性绩效的理论调查有利于了解GNN模型的基本问题(如公平性)和设计更好的学习方法。在本文中,我们在非IID半监督学习设置下为GNN提供了一种新的PAC-Bayesian分析。此外,我们分析了未标记节点的不同子组上的泛化性能,这使我们能够通过理论观点进一步研究GNN的准确性 - (DIS)奇偶校准风格(UN)公平。在合理的假设下,我们证明了测试子组和训练集之间的距离可以是影响该子组上GNN性能的关键因素,这调用了对公平学习的培训节点选择。多个GNN模型和数据集的实验支持我们的理论结果。
translated by 谷歌翻译
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。
translated by 谷歌翻译
图表神经网络(GNNS)对于节点分类或边缘预测等预测任务,在最近的机器中从图形结构数据中获得了越来越长的注意。然而,难以获得大量标记的图表,这显着限制了GNN的真正成功。虽然积极学习已被广​​泛研究用于解决文本,图像等等其他数据类型的标签稀疏问题,但如何使其有效地对图表进行有效,是一个开放的研究问题。在本文中,我们对节点分类任务的GNN进行了主动学习的调查。具体地,我们提出了一种新方法,它使用节点特征传播,然后是节点的K-METOIDS聚类,例如在活动学习中选择。通过理论束缚分析,我们证明了我们的方法的设计选择。在我们在四个基准数据集的实验中,所提出的方法始终如一地优于其他代表性基线方法。
translated by 谷歌翻译
近年来,监督学习环境的几个结果表明,古典统计学习 - 理论措施,如VC维度,不充分解释深度学习模型的性能,促使在无限宽度和迭代制度中的工作摆动。但是,对于超出监督环境之外的神经网络成功几乎没有理论解释。在本文中,我们认为,在一些分布假设下,经典学习 - 理论措施可以充分解释转导造型中的图形神经网络的概括。特别是,我们通过分析节点分类问题图卷积网络的概括性特性,对神经网络的性能进行严格分析神经网络。虽然VC维度确实导致该设置中的琐碎泛化误差界限,但我们表明转导变速器复杂性可以解释用于随机块模型的图形卷积网络的泛化特性。我们进一步使用基于转换的Rademacher复杂性的泛化误差界限来展示图形卷积和网络架构在实现较小的泛化误差方面的作用,并在图形结构可以帮助学习时提供洞察。本文的调查结果可以重新新的兴趣在学习理论措施方面对神经网络的概括,尽管在特定问题中。
translated by 谷歌翻译
Graph neural networks (GNN) have become the default machine learning model for relational datasets, including protein interaction networks, biological neural networks, and scientific collaboration graphs. We use tools from statistical physics and random matrix theory to precisely characterize generalization in simple graph convolution networks on the contextual stochastic block model. The derived curves are phenomenologically rich: they explain the distinction between learning on homophilic and heterophilic graphs and they predict double descent whose existence in GNNs has been questioned by recent work. Our results are the first to accurately explain the behavior not only of a stylized graph learning model but also of complex GNNs on messy real-world datasets. To wit, we use our analytic insights about homophily and heterophily to improve performance of state-of-the-art graph neural networks on several heterophilic benchmarks by a simple addition of negative self-loop filters.
translated by 谷歌翻译
这项工作提供了有关图消息传递神经网络(GMPNNS)(例如图形神经网络(GNNS))的第一个理论研究,以执行归纳性脱离分布(OOD)链接预测任务,在部署(测试)(测试))图大小比训练图大。我们首先证明了非反应界限,表明基于GMPNN获得的基于置换 - 等值的(结构)节点嵌入的链接预测变量可以随着测试图变大,可以收敛到随机猜测。然后,我们提出了一个理论上的GMPNN,该GMPNN输出结构性成对(2节点)嵌入,并证明非扰动边界表明,随着测试图的增长,这些嵌入量会收敛到连续函数的嵌入,以保留其预测链接的能力。随机图上的经验结果表明与我们的理论结果一致。
translated by 谷歌翻译
图卷积网络(GCN)最近在学习图形结构数据方面取得了巨大的经验成功。为了解决由于相邻特征的递归嵌入而导致的可伸缩性问题,已经提出了图形拓扑抽样来降低训练GCN的记忆和计算成本,并且在许多经验研究中,它与没有拓扑采样的人达到了可比的测试性能。据我们所知,本文为半监督节点分类的训练(最多)三层GCN提供了图形拓扑采样的第一个理论理由。我们正式表征了图形拓扑抽样的一些足够条件,以使GCN训练导致概括误差减少。此外,我们的方法可以解决跨层的重量的非凸相互作用,这在GCN的现有理论分析中尚未探索。本文表征了图结构和拓扑抽样对概括性能和样本复杂性的影响,理论发现也通过数值实验证明了合理性。
translated by 谷歌翻译
通过递归将整个社区的节点特征汇总,空间图卷积运算符已被宣布为图形神经网络(GNNS)成功的关键。然而,尽管GNN方法跨任务和应用程序进行了繁殖,但此聚合操作对其性能的影响尚未得到广泛的分析。实际上,尽管努力主要集中于优化神经网络的体系结构,但更少的工作试图表征(a)不同类别的空间卷积操作员,(b)特定类别的选择如何与数据的属性相关,以及(c)它对嵌入空间的几何形状的影响。在本文中,我们建议通过将现有操作员分为两个主要类(对称性与行规范的空间卷积)来回答所有三个问题,并展示它们如何转化为数据性质的不同隐性偏见。最后,我们表明,这种聚合操作员实际上是可调的,并且明确的制度在其中某些操作员(因此,嵌入几何形状)的某些选择可能更合适。
translated by 谷歌翻译
随机奇异值分解(RSVD)是用于计算大型数据矩阵截断的SVD的一类计算算法。给定A $ n \ times n $对称矩阵$ \ mathbf {m} $,原型RSVD算法输出通过计算$ \ mathbf {m mathbf {m} $的$ k $引导singular vectors的近似m}^{g} \ mathbf {g} $;这里$ g \ geq 1 $是一个整数,$ \ mathbf {g} \ in \ mathbb {r}^{n \ times k} $是一个随机的高斯素描矩阵。在本文中,我们研究了一般的“信号加上噪声”框架下的RSVD的统计特性,即,观察到的矩阵$ \ hat {\ mathbf {m}} $被认为是某种真实但未知的加法扰动信号矩阵$ \ mathbf {m} $。我们首先得出$ \ ell_2 $(频谱规范)和$ \ ell_ {2 \ to \ infty} $(最大行行列$ \ ell_2 $ norm)$ \ hat {\ hat {\ Mathbf {M}} $和信号矩阵$ \ Mathbf {M} $的真实单数向量。这些上限取决于信噪比(SNR)和功率迭代$ g $的数量。观察到一个相变现象,其中较小的SNR需要较大的$ g $值以保证$ \ ell_2 $和$ \ ell_ {2 \ to \ fo \ infty} $ distances的收敛。我们还表明,每当噪声矩阵满足一定的痕量生长条件时,这些相变发生的$ g $的阈值都会很清晰。最后,我们得出了近似奇异向量的行波和近似矩阵的进入波动的正常近似。我们通过将RSVD的几乎最佳性能保证在应用于三个统计推断问题的情况下,即社区检测,矩阵完成和主要的组件分析,并使用缺失的数据来说明我们的理论结果。
translated by 谷歌翻译
为了捕获许多社区检测问题的固有几何特征,我们建议使用一个新的社区随机图模型,我们称之为\ emph {几何块模型}。几何模型建立在\ emph {随机几何图}(Gilbert,1961)上,这是空间网络的随机图的基本模型之一,就像在ERD \ H上建立的良好的随机块模型一样{o} s-r \'{en} yi随机图。它也是受到社区发现中最新的理论和实际进步启发的随机社区模型的自然扩展。为了分析几何模型,我们首先为\ emph {Random Annulus图}提供新的连接结果,这是随机几何图的概括。自引入以来,已经研究了几何图的连通性特性,并且由于相关的边缘形成而很难分析它们。然后,我们使用随机环形图的连接结果来提供必要的条件,以有效地为几何块模型恢复社区。我们表明,一种简单的三角计数算法来检测几何模型中的社区几乎是最佳的。为此,我们考虑了两个图密度方案。在图表的平均程度随着顶点的对数增长的状态中,我们表明我们的算法在理论上和实际上都表现出色。相比之下,三角计数算法对于对数学度方案中随机块模型远非最佳。我们还查看了图表的平均度与顶点$ n $的数量线性增长的状态,因此要存储一个需要$ \ theta(n^2)$内存的图表。我们表明,我们的算法需要在此制度中仅存储$ o(n \ log n)$边缘以恢复潜在社区。
translated by 谷歌翻译
Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) their predictive performance as we pile up many layers and add non-lineality. To tackle this problem, we investigate the expressive power of graph NNs via their asymptotic behaviors as the layer size tends to infinity. Our strategy is to generalize the forward propagation of a Graph Convolutional Network (GCN), which is a popular graph NN variant, as a specific dynamical system. In the case of a GCN, we show that when its weights satisfy the conditions determined by the spectra of the (augmented) normalized Laplacian, its output exponentially approaches the set of signals that carry information of the connected components and node degrees only for distinguishing nodes. Our theory enables us to relate the expressive power of GCNs with the topological information of the underlying graphs inherent in the graph spectra. To demonstrate this, we characterize the asymptotic behavior of GCNs on the Erdős -Rényi graph. We show that when the Erdős -Rényi graph is sufficiently dense and large, a broad range of GCNs on it suffers from the "information loss" in the limit of infinite layers with high probability. Based on the theory, we provide a principled guideline for weight normalization of graph NNs. We experimentally confirm that the proposed weight scaling enhances the predictive performance of GCNs in real data 1 .
translated by 谷歌翻译
我们调查与高斯的混合的数据分享共同但未知,潜在虐待协方差矩阵的数据。我们首先考虑具有两个等级大小的组件的高斯混合,并根据最大似然估计导出最大切割整数程序。当样品的数量在维度下线性增长时,我们证明其解决方案实现了最佳的错误分类率,直到对数因子。但是,解决最大切割问题似乎是在计算上棘手的。为了克服这一点,我们开发了一种高效的频谱算法,该算法达到最佳速率,但需要一种二次样本量。虽然这种样本复杂性比最大切割问题更差,但我们猜测没有多项式方法可以更好地执行。此外,我们收集了支持统计计算差距存在的数值和理论证据。最后,我们将MAX-CUT程序概括为$ k $ -means程序,该程序处理多组分混合物的可能性不平等。它享有相似的最优性保证,用于满足运输成本不平等的分布式的混合物,包括高斯和强烈的对数的分布。
translated by 谷歌翻译
我们研究了从高阶图卷积中的有效学习,并直接从邻接矩阵进行节点分类学习。我们重新访问缩放的图形残留网络,并从残留层中删除Relu激活,并在每个残留层上应用一个重量矩阵。我们表明,所得模型导致新的图卷积模型作为归一化邻接矩阵,残留权重矩阵和残差缩放参数的多项式。此外,我们提出了直接绘制多项式卷积模型和直接从邻接矩阵学习的自适应学习。此外,我们提出了完全自适应模型,以学习每个残留层的缩放参数。我们表明,所提出的方法的概括界限是特征值谱,缩放参数和残留权重的上限的多项式。通过理论分析,我们认为所提出的模型可以通过限制卷积的更高端口和直接从邻接矩阵学习来获得改进的概括界限。我们使用一套真实数据,我们证明所提出的方法获得了提高的非全粒图淋巴结分类的精度。
translated by 谷歌翻译
Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence. To better understand this phenomenon, we study adversarially robust learning from the viewpoint of generalization. We show that already in a simple natural data model, the sample complexity of robust learning can be significantly larger than that of "standard" learning. This gap is information theoretic and holds irrespective of the training algorithm or the model family. We complement our theoretical results with experiments on popular image classification datasets and show that a similar gap exists here as well. We postulate that the difficulty of training robust classifiers stems, at least partially, from this inherently larger sample complexity.
translated by 谷歌翻译
我们研究了深GCN模型中的自适应层图形卷积。我们建议ADAGPR在GCNII网络的每一层中学习通用的Pageranks,以诱导适应性卷积。我们表明,ADAGPR结合的概括是由归一化邻接矩阵的特征值谱的多项式按概括性Pagerank系数数量的顺序界定的。通过分析概括范围,我们表明过度厚度取决于汇总的较高阶段矩阵矩阵和模型深度。我们使用基准真实数据对节点分类进行了评估,并表明ADAGPR与现有的图形卷积网络相比提供了改进的精确度,同时证明了针对超平面的稳健性。此外,我们证明了对层概括的PageRanks系数的分析使我们能够在每个层上定性地了解模型解释的卷积。
translated by 谷歌翻译
This article explores and analyzes the unsupervised clustering of large partially observed graphs. We propose a scalable and provable randomized framework for clustering graphs generated from the stochastic block model. The clustering is first applied to a sub-matrix of the graph's adjacency matrix associated with a reduced graph sketch constructed using random sampling. Then, the clusters of the full graph are inferred based on the clusters extracted from the sketch using a correlation-based retrieval step. Uniform random node sampling is shown to improve the computational complexity over clustering of the full graph when the cluster sizes are balanced. A new random degree-based node sampling algorithm is presented which significantly improves upon the performance of the clustering algorithm even when clusters are unbalanced. This framework improves the phase transitions for matrix-decomposition-based clustering with regard to computational complexity and minimum cluster size, which are shown to be nearly dimension-free in the low inter-cluster connectivity regime. A third sampling technique is shown to improve balance by randomly sampling nodes based on spatial distribution. We provide analysis and numerical results using a convex clustering algorithm based on matrix completion.
translated by 谷歌翻译