图神经网络(GNN)已证明其在各种应用中的表现出色。然而,其背后的工作机制仍然神秘。 GNN模型旨在学习图形结构数据的有效表示,该数据本质上与图形信号denoising(GSD)的原理相吻合。算法展开是一种“学习优化”技术的算法,由于其在构建高效和可解释的神经网络体系结构方面的前景,人们引起了人们的关注。在本文中,我们引入了基于GSD问题的截断优化算法(例如梯度下降和近端梯度下降)构建的一类展开网络。它们被证明与许多流行的GNN模型紧密相连,因为这些GNN中的正向传播实际上是为特定GSD提供服务的展开网络。此外,可以将GNN模型的训练过程视为解决了较低级别的GSD问题的双重优化问题。这种连接带来了GNN的新景,因为我们可以尝试从GSD对应物中理解它们的实际功能,并且还可以激励设计新的GNN模型。基于算法展开的观点,一种名为UGDGNN的表达模型,即展开的梯度下降GNN,进一步提出了继承具有吸引力的理论属性的。七个基准数据集上的大量数值模拟表明,UGDGNN可以比最新模型实现卓越或竞争性的性能。
translated by 谷歌翻译
Graph neural networks (GNNs) have shown remarkable performance on homophilic graph data while being far less impressive when handling non-homophilic graph data due to the inherent low-pass filtering property of GNNs. In general, since the real-world graphs are often a complex mixture of diverse subgraph patterns, learning a universal spectral filter on the graph from the global perspective as in most current works may still suffer from great difficulty in adapting to the variation of local patterns. On the basis of the theoretical analysis on local patterns, we rethink the existing spectral filtering methods and propose the \textbf{\underline{N}}ode-oriented spectral \textbf{\underline{F}}iltering for \textbf{\underline{G}}raph \textbf{\underline{N}}eural \textbf{\underline{N}}etwork (namely NFGNN). By estimating the node-oriented spectral filter for each node, NFGNN is provided with the capability of precise local node positioning via the generalized translated operator, thus discriminating the variations of local homophily patterns adaptively. Meanwhile, the utilization of re-parameterization brings a good trade-off between global consistency and local sensibility for learning the node-oriented spectral filters. Furthermore, we theoretically analyze the localization property of NFGNN, demonstrating that the signal after adaptive filtering is still positioned around the corresponding node. Extensive experimental results demonstrate that the proposed NFGNN achieves more favorable performance.
translated by 谷歌翻译
Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the over-smoothing problem.In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: Initial residual and Identity mapping. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi-and fullsupervised tasks. Code is available at https: //github.com/chennnM/GCNII.
translated by 谷歌翻译
图形神经网络(GNNS)对图表上的半监督节点分类展示了卓越的性能,结果是它们能够同时利用节点特征和拓扑信息的能力。然而,大多数GNN隐含地假设曲线图中的节点和其邻居的标签是相同或一致的,其不包含在异质图中,其中链接节点的标签可能不同。因此,当拓扑是非信息性的标签预测时,普通的GNN可以显着更差,而不是在每个节点上施加多层Perceptrons(MLPS)。为了解决上述问题,我们提出了一种新的$ -laplacian基于GNN模型,称为$ ^ P $ GNN,其消息传递机制来自离散正则化框架,并且可以理论上解释为多项式图的近似值在$ p $ -laplacians的频谱域上定义过滤器。光谱分析表明,新的消息传递机制同时用作低通和高通滤波器,从而使$ ^ P $ GNNS对同性恋和异化图有效。关于现实世界和合成数据集的实证研究验证了我们的调查结果,并证明了$ ^ P $ GNN明显优于异交基准的几个最先进的GNN架构,同时在同性恋基准上实现竞争性能。此外,$ ^ p $ gnns可以自适应地学习聚合权重,并且对嘈杂的边缘具有强大。
translated by 谷歌翻译
Deep learning has been shown to be successful in a number of domains, ranging from acoustics, images, to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics of graphs. Recently, substantial research efforts have been devoted to applying deep learning methods to graphs, resulting in beneficial advances in graph analysis techniques. In this survey, we comprehensively review the different types of deep learning methods on graphs. We divide the existing methods into five categories based on their model architectures and training strategies: graph recurrent neural networks, graph convolutional networks, graph autoencoders, graph reinforcement learning, and graph adversarial methods. We then provide a comprehensive overview of these methods in a systematic manner mainly by following their development history. We also analyze the differences and compositions of different methods. Finally, we briefly outline the applications in which they have been used and discuss potential future research directions.
translated by 谷歌翻译
随着从现实世界所收集的图形数据仅仅是无噪声,图形的实际表示应该是强大的噪声。现有的研究通常侧重于特征平滑,但留下几何结构不受影响。此外,大多数工作需要L2-Norm,追求全局平滑度,这限制了图形神经网络的表现。本文根据特征和结构噪声裁定图表数据的常规程序,其中目标函数用乘法器(ADMM)的交替方向方法有效地解决。该方案允许采用多个层,而无需过平滑的关注,并且保证对最佳解决方案的收敛性。实证研究证明,即使在重大污染的情况下,我们的模型也与流行的图表卷积相比具有明显更好的性能。
translated by 谷歌翻译
尽管近期图形神经网络(GNN)成功,但常见的架构通常表现出显着的限制,包括对过天飞机,远程依赖性和杂散边缘的敏感性,例如,由于图形异常或对抗性攻击。至少部分地解决了一个简单的透明框架内的这些问题,我们考虑了一个新的GNN层系列,旨在模仿和整合两个经典迭代算法的更新规则,即近端梯度下降和迭代重复最小二乘(IRLS)。前者定义了一个可扩展的基础GNN架构,其免受过性的,而仍然可以通过允许任意传播步骤捕获远程依赖性。相反,后者产生了一种新颖的注意机制,该注意机制被明确地锚定到底层端到端能量函数,以及相对于边缘不确定性的稳定性。当结合时,我们获得了一个非常简单而强大的模型,我们在包括标准化基准,与异常扰动的图形,具有异化的图形和涉及远程依赖性的图形的不同方案的极其简单而强大的模型。在此过程中,我们与已明确为各个任务设计的SOTA GNN方法进行比较,实现竞争或卓越的节点分类准确性。我们的代码可以在https://github.com/fftyyy/twirls获得。
translated by 谷歌翻译
消息传递已作为设计图形神经网络(GNN)的有效工具的发展。但是,消息传递的大多数现有方法简单地简单或平均所有相邻的功能更新节点表示。它们受到两个问题的限制,即(i)缺乏可解释性来识别对GNN的预测重要的节点特征,以及(ii)特征过度混合,导致捕获长期依赖和无能为力的过度平滑问题在异质或低同质的下方处理图。在本文中,我们提出了一个节点级胶囊图神经网络(NCGNN),以通过改进的消息传递方案来解决这些问题。具体而言,NCGNN表示节点为节点级胶囊组,其中每个胶囊都提取其相应节点的独特特征。对于每个节点级胶囊,开发了一个新颖的动态路由过程,以适应适当的胶囊,以从设计的图形滤波器确定的子图中聚集。 NCGNN聚集仅有利的胶囊并限制无关的消息,以避免交互节点的过度混合特征。因此,它可以缓解过度平滑的问题,并通过同粒或异质的图表学习有效的节点表示。此外,我们提出的消息传递方案本质上是可解释的,并免于复杂的事后解释,因为图形过滤器和动态路由过程确定了节点特征的子集,这对于从提取的子分类中的模型预测最为重要。关于合成和现实图形的广泛实验表明,NCGNN可以很好地解决过度光滑的问题,并为半监视的节点分类产生更好的节点表示。它的表现优于同质和异质的艺术状态。
translated by 谷歌翻译
由于问题过度问题,大多数现有的图形神经网络只能使用其固有有限的聚合层捕获有限的依赖性。为了克服这一限制,我们提出了一种新型的图形卷积,称为图形隐式非线性扩散(GIND),该卷积隐含地可以访问邻居的无限啤酒花,同时具有非线性扩散的自适应聚集特征,以防止过度张开。值得注意的是,我们表明,学到的表示形式可以正式化为显式凸优化目标的最小化器。有了这个属性,我们可以从优化的角度从理论上表征GIND的平衡。更有趣的是,我们可以通过修改相应的优化目标来诱导新的结构变体。具体而言,我们可以将先前的特性嵌入到平衡中,并引入跳过连接以促进训练稳定性。广泛的实验表明,GIND擅长捕获长期依赖性,并且在具有非线性扩散的同粒细胞和异性图上表现良好。此外,我们表明,我们模型的优化引起的变体可以提高性能并提高训练稳定性和效率。结果,我们的GIND在节点级别和图形级任务上都获得了重大改进。
translated by 谷歌翻译
作为建模复杂关系的强大工具,HyperGraphs从图表学习社区中获得了流行。但是,深度刻画学习中的常用框架专注于具有边缘独立的顶点权重(EIVW)的超图,而无需考虑具有具有更多建模功率的边缘依赖性顶点权重(EDVWS)的超图。为了弥补这一点,我们提出了一般的超图光谱卷积(GHSC),这是一个通用学习框架,不仅可以处理EDVW和EIVW HyperGraphs,而且更重要的是,理论上可以明确地利用现有强大的图形卷积神经网络(GCNN)明确说明,从而很大程度上可以释放。超图神经网络的设计。在此框架中,给定的无向GCNN的图形拉普拉斯被统一的HyperGraph Laplacian替换,该统一的HyperGraph Laplacian通过将我们所定义的广义超透明牌与简单的无向图等同起来,从随机的步行角度将顶点权重信息替换。来自各个领域的广泛实验,包括社交网络分析,视觉目标分类和蛋白质学习,证明了拟议框架的最新性能。
translated by 谷歌翻译
图形神经网络已成为从图形结构数据学习的不可缺少的工具之一,并且它们的实用性已在各种各样的任务中显示。近年来,建筑设计的巨大改进,导致各种预测任务的性能更好。通常,这些神经架构在同一层中使用可知的权重矩阵组合节点特征聚合和特征转换。这使得分析从各种跳过的节点特征和神经网络层的富有效力来挑战。由于不同的图形数据集显示在特征和类标签分布中的不同级别和异常级别,因此必须了解哪些特征对于没有任何先前信息的预测任务是重要的。在这项工作中,我们将节点特征聚合步骤和深度与图形神经网络分离,并经验分析了不同的聚合特征在预测性能中发挥作用。我们表明,并非通过聚合步骤生成的所有功能都很有用,并且通常使用这些较少的信息特征可能对GNN模型的性能有害。通过我们的实验,我们表明学习这些功能的某些子集可能会导致各种数据集的性能更好。我们建议使用Softmax作为常规器,并从不同跳距的邻居聚合的功能的“软选择器”;和L2 - GNN层的标准化。结合这些技术,我们呈现了一个简单浅的模型,特征选择图神经网络(FSGNN),并经验展示所提出的模型比九个基准数据集中的最先进的GNN模型实现了可比或甚至更高的准确性节点分类任务,具有显着的改进,可达51.1%。
translated by 谷歌翻译
Graph classification is an important area in both modern research and industry. Multiple applications, especially in chemistry and novel drug discovery, encourage rapid development of machine learning models in this area. To keep up with the pace of new research, proper experimental design, fair evaluation, and independent benchmarks are essential. Design of strong baselines is an indispensable element of such works. In this thesis, we explore multiple approaches to graph classification. We focus on Graph Neural Networks (GNNs), which emerged as a de facto standard deep learning technique for graph representation learning. Classical approaches, such as graph descriptors and molecular fingerprints, are also addressed. We design fair evaluation experimental protocol and choose proper datasets collection. This allows us to perform numerous experiments and rigorously analyze modern approaches. We arrive to many conclusions, which shed new light on performance and quality of novel algorithms. We investigate application of Jumping Knowledge GNN architecture to graph classification, which proves to be an efficient tool for improving base graph neural network architectures. Multiple improvements to baseline models are also proposed and experimentally verified, which constitutes an important contribution to the field of fair model comparison.
translated by 谷歌翻译
Graph neural networks have shown significant success in the field of graph representation learning. Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Nevertheless, one layer of these neighborhood aggregation methods only consider immediate neighbors, and the performance decreases when going deeper to enable larger receptive fields. Several recent studies attribute this performance deterioration to the over-smoothing issue, which states that repeated propagation makes node representations of different classes indistinguishable. In this work, we study this observation systematically and develop new insights towards deeper graph neural networks. First, we provide a systematical analysis on this issue and argue that the key factor compromising the performance significantly is the entanglement of representation transformation and propagation in current graph convolution operations. After decoupling these two operations, deeper graph neural networks can be used to learn graph node representations from larger receptive fields. We further provide a theoretical analysis of the above observation when building very deep models, which can serve as a rigorous and gentle description of the over-smoothing issue. Based on our theoretical and empirical analysis, we propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields. A set of experiments on citation, coauthorship, and co-purchase datasets have confirmed our analysis and insights and demonstrated the superiority of our proposed methods. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Artificial intelligence; Neural networks.
translated by 谷歌翻译
最新提出的基于变压器的图形模型的作品证明了香草变压器用于图形表示学习的不足。要了解这种不足,需要研究变压器的光谱分析是否会揭示其对其表现力的见解。类似的研究已经确定,图神经网络(GNN)的光谱分析为其表现力提供了额外的观点。在这项工作中,我们系统地研究并建立了变压器领域中的空间和光谱域之间的联系。我们进一步提供了理论分析,并证明了变压器中的空间注意机制无法有效捕获所需的频率响应,因此,固有地限制了其在光谱空间中的表现力。因此,我们提出了feta,该框架旨在在整个图形频谱(即图形的实际频率成分)上进行注意力类似于空间空间中的注意力。经验结果表明,FETA在标准基准的所有任务中为香草变压器提供均匀的性能增益,并且可以轻松地扩展到具有低通特性的基于GNN的模型(例如GAT)。
translated by 谷歌翻译
几何深度学习取得了长足的进步,旨在概括从传统领域到非欧几里得群岛的结构感知神经网络的设计,从而引起图形神经网络(GNN),这些神经网络(GNN)可以应用于形成的图形结构数据,例如社会,例如,网络,生物化学和材料科学。尤其是受欧几里得对应物的启发,尤其是图形卷积网络(GCN)通过提取结构感知功能来成功处理图形数据。但是,当前的GNN模型通常受到各种现象的限制,这些现象限制了其表达能力和推广到更复杂的图形数据集的能力。大多数模型基本上依赖于通过本地平均操作对图形信号的低通滤波,从而导致过度平滑。此外,为了避免严重的过度厚度,大多数流行的GCN式网络往往是较浅的,并且具有狭窄的接收场,导致侵犯。在这里,我们提出了一个混合GNN框架,该框架将传统的GCN过滤器与通过几何散射定义的带通滤波器相结合。我们进一步介绍了一个注意框架,该框架允许该模型在节点级别上从不同过滤器的组合信息进行本地参与。我们的理论结果确定了散射过滤器的互补益处,以利用图表中的结构信息,而我们的实验显示了我们方法对各种学习任务的好处。
translated by 谷歌翻译
光谱图神经网络是基于图信号过滤器的一种图神经网络(GNN)。一些能够学习任意光谱过滤器的模型最近出现了。但是,很少有作品分析光谱GNN的表达能力。本文理论上研究了光谱GNNS的表现力。我们首先证明,即使没有非线性的光谱GNN也可以产生任意的图形信号,并给出了两个条件以达到普遍性。它们是:1)图Laplacian的多个特征值和2)节点特征中没有缺失的频率组件。我们还建立了光谱GNN的表达能力与图形同构(GI)测试之间的联系,后者通常用于表征空间GNNS的表达能力。此外,我们从优化的角度研究了具有相同表达能力的不同光谱GNN之间的经验性能差异,并激发了其重量函数对应于光谱中图信号密度的正交基础的使用。受分析的启发,我们提出了Jacobiconv,该雅各比基的正交性和灵活性使用了雅各比的基础,以适应广泛的重量功能。 Jacobiconv抛弃了非线性,同时在合成和现实世界数据集上都超过了所有基线。
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
Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Chebyshev polynomial achieves the optimum convergent rate for approximating a function. In this paper, we revisit the problem of approximating the spectral graph convolutions with Chebyshev polynomials. We show that ChebNet's inferior performance is primarily due to illegal coefficients learnt by ChebNet approximating analytic filter functions, which leads to over-fitting. We then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomenon. We conducted an extensive experimental study to demonstrate that ChebNetII can learn arbitrary graph convolutions and achieve superior performance in both full- and semi-supervised node classification tasks. Most notably, we scale ChebNetII to a billion graph ogbn-papers100M, showing that spectral-based GNNs have superior performance. Our code is available at https://github.com/ivam-he/ChebNetII.
translated by 谷歌翻译
过度平滑是一个具有挑战性的问题,这会降低深图卷积网络(GCNS)的性能。然而,用于缓解过度平滑问题的现有研究缺乏一般性或有效性。在本文中,我们分析了过度平滑问题背后的潜在问题,即特征 - 多样性退化,梯度消失和模型重量衰减。灵感来自于此,我们提出了一个简单而有效的即插即用模块,速度,缓解过度平滑。具体地,对于GCN模型的每个中间层,随机地(或基于节点度)选择节点以通过直接向非线性函数馈送它们的输入特征来跳过卷积操作。分析,1)跳过卷积操作可以防止特征失去多样性; 2)“跳过”节点使能梯度直接传递回来,从而减轻梯度消失和模型权重过腐蚀问题。为了展示Skipnode的优越性,我们对九个流行的数据集进行了广泛的实验,包括同性恋和异化图,在两个典型的任务上具有不同的图表大小:节点分类和链路预测。具体而言,1)SkipNode具有适应不同数据集和任务的各种基于GCN的模型的普遍性。 2)Skipnode优于最近最先进的反平滑插头 - 播放模块,即DropEdge和Dropnode,在不同的设置中。代码将在GitHub上公开提供。
translated by 谷歌翻译
提高GCN的深度(预计将允许更多表达性)显示出损害性能,尤其是在节点分类上。原因的主要原因在于过度平滑。过度平滑的问题将GCN的输出驱动到一个在节点之间包含有限的区别信息的空间,从而导致表现不佳。已经提出了一些有关完善GCN架构的作品,但理论上仍然未知这些改进是否能够缓解过度平衡。在本文中,我们首先从理论上分析了通用GCN如何与深度增加的作用,包括通用GCN,GCN,具有偏见,RESGCN和APPNP。我们发现所有这些模型都以通用过程为特征:所有节点融合到Cuboid。在该定理下,我们建议通过在每个训练时期随机去除一定数量的边缘来减轻过度光滑的状态。从理论上讲,Dropedge可以降低过度平滑的收敛速度,或者可以减轻尺寸崩溃引起的信息损失。对模拟数据集的实验评估已可视化不同GCN之间过度平滑的差异。此外,对几个真正的基准支持的广泛实验,这些实验始终如一地改善各种浅GCN和深度GCN的性能。
translated by 谷歌翻译