Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes. While conventional wisdom largely attributes the success of GNNs to their advanced expressivity for learning desired functions on nodes' ego-graphs, we conjecture that this is \emph{not} the main cause of GNNs' superiority in node prediction tasks. This paper pinpoints the major source of GNNs' performance gain to their intrinsic generalization capabilities, by introducing an intermediate model class dubbed as P(ropagational)MLP, which is identical to standard MLP in training, and then adopt GNN's architecture in testing. Intriguingly, we observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts across ten benchmarks and different experimental settings, despite the fact that PMLPs share the same (trained) weights with poorly-performed MLP. This critical finding opens a door to a brand new perspective for understanding the power of GNNs, and allow bridging GNNs and MLPs for dissecting their generalization behaviors. As an initial step to analyze PMLP, we show its essential difference with MLP at infinite-width limit lies in the NTK feature map in the post-training stage. Moreover, though MLP and PMLP cannot extrapolate non-linear functions for extreme OOD data, PMLP has more freedom to generalize near the training support.
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
图形神经网络(GNNS)由于其强大的表示能力而广泛用于图形结构化数据处理。通常认为,GNNS可以隐式消除非预测性的噪音。但是,对图神经网络中隐式降解作用的分析仍然开放。在这项工作中,我们进行了一项全面的理论研究,并分析了隐式denoising在GNN中发生的何时以及为什么发生。具体而言,我们研究噪声矩阵的收敛性。我们的理论分析表明,隐式转化很大程度上取决于连接性,图形大小和GNN体系结构。此外,我们通过扩展图形信号降解问题来正式定义并提出对抗图信号denoising(AGSD)问题。通过解决这样的问题,我们得出了一个可靠的图形卷积,可以增强节点表示的平滑度和隐式转化效果。广泛的经验评估验证了我们的理论分析和我们提出的模型的有效性。
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
尽管在深度学习的其他应用领域中取得了非常深的架构,但流行的图神经网络是浅层模型。这降低了建模能力,并使模型无法捕获远程关系。浅设计的主要原因是过度平滑的,这导致节点状态随着深度的增加而变得更加相似。我们建立在GNNS和Pagerank之间的紧密联系的基础上,为此,个性化的Pagerank介绍了对个性化向量的考虑。通过这个想法,我们提出了个性化的Pagerank图神经网络(PPRGNN),该神经网络将图形卷积网络扩展到无限深度模型,该模型有机会将邻居聚集重置回每个迭代中的初始状态。我们引入了一个很好的解释调整,以重置重置并证明我们的方法与独特解决方案的收敛性,而无需放置任何限制,即使无限地进行了许多邻居聚集。与个性化的Pagerank一样,我们的结果不会过度光滑。在这样做的同时,在我们保持内存复杂性恒定的同时,时间复杂性保持线性,而与网络的深度无关,使其比较大图。我们从经验上展示了方法对各种节点和图形分类任务的有效性。在几乎所有情况下,PPRGNN优于可比较的方法。
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) are powerful tools for graph representation learning. Despite their rapid development, GNNs also face some challenges, such as over-fitting, over-smoothing, and non-robustness. Previous works indicate that these problems can be alleviated by random dropping methods, which integrate augmented data into models by randomly masking parts of the input. However, some open problems of random dropping on GNNs remain to be solved. First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models. Second, augmented data introduced to GNNs causes the incomplete coverage of parameters and unstable training process. Third, there is no theoretical analysis on the effectiveness of random dropping methods on GNNs. In this paper, we propose a novel random dropping method called DropMessage, which performs dropping operations directly on the propagated messages during the message-passing process. More importantly, we find that DropMessage provides a unified framework for most existing random dropping methods, based on which we give theoretical analysis of their effectiveness. Furthermore, we elaborate the superiority of DropMessage: it stabilizes the training process by reducing sample variance; it keeps information diversity from the perspective of information theory, enabling it become a theoretical upper bound of other methods. To evaluate our proposed method, we conduct experiments that aims for multiple tasks on five public datasets and two industrial datasets with various backbone models. The experimental results show that DropMessage has the advantages of both effectiveness and generalization, and can significantly alleviate the problems mentioned above.
translated by 谷歌翻译
Pre-publication draft of a book to be published byMorgan & Claypool publishers. Unedited version released with permission. All relevant copyrights held by the author and publisher extend to this pre-publication draft.
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
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
Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications. One reason for this academic-industrial gap is the neighborhood-fetching latency incurred by data dependency in GNNs, which make it hard to deploy for latency-sensitive applications that require fast inference. Conversely, without involving any feature aggregation, MLPs have no data dependency and infer much faster than GNNs, but their performance is less competitive. Motivated by these complementary strengths and weaknesses, we propose a Graph Self-Distillation on Neighborhood (GSDN) framework to reduce the gap between GNNs and MLPs. Specifically, the GSDN framework is based purely on MLPs, where structural information is only implicitly used as prior to guide knowledge self-distillation between the neighborhood and the target, substituting the explicit neighborhood information propagation as in GNNs. As a result, GSDN enjoys the benefits of graph topology-awareness in training but has no data dependency in inference. Extensive experiments have shown that the performance of vanilla MLPs can be greatly improved with self-distillation, e.g., GSDN improves over stand-alone MLPs by 15.54\% on average and outperforms the state-of-the-art GNNs on six datasets. Regarding inference speed, GSDN infers 75X-89X faster than existing GNNs and 16X-25X faster than other inference acceleration methods.
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
图形神经网络(GNN)在许多基于图的任务中表现出强大的表示能力。具体而言,由于其简单性和性能优势,GNN(例如APPNP)的解耦结构变得流行。但是,这些GNN的端到端培训使它们在计算和记忆消耗方面效率低下。为了应对这些局限性,在这项工作中,我们为图形神经网络提供了交替的优化框架,不需要端到端培训。在不同设置下进行的广泛实验表明,所提出的算法的性能与现有的最新算法相当,但具有更好的计算和记忆效率。此外,我们表明我们的框架可以利用优势来增强现有的脱钩GNN。
translated by 谷歌翻译
Graph Neural Networks (GNNs) have been predominant for graph learning tasks; however, recent studies showed that a well-known graph algorithm, Label Propagation (LP), combined with a shallow neural network can achieve comparable performance to GNNs in semi-supervised node classification on graphs with high homophily. In this paper, we show that this approach falls short on graphs with low homophily, where nodes often connect to the nodes of the opposite classes. To overcome this, we carefully design a combination of a base predictor with LP algorithm that enjoys a closed-form solution as well as convergence guarantees. Our algorithm first learns the class compatibility matrix and then aggregates label predictions using LP algorithm weighted by class compatibilities. On a wide variety of benchmarks, we show that our approach achieves the leading performance on graphs with various levels of homophily. Meanwhile, it has orders of magnitude fewer parameters and requires less execution time. Empirical evaluations demonstrate that simple adaptations of LP can be competitive in semi-supervised node classification in both homophily and heterophily regimes.
translated by 谷歌翻译
图表是一个宇宙数据结构,广泛用于组织现实世界中的数据。像交通网络,社交和学术网络这样的各种实际网络网络可以由图表代表。近年来,目睹了在网络中代表顶点的快速发展,进入低维矢量空间,称为网络表示学习。表示学习可以促进图形数据上的新算法的设计。在本调查中,我们对网络代表学习的当前文献进行了全面审查。现有算法可以分为三组:浅埋模型,异构网络嵌入模型,图形神经网络的模型。我们为每个类别审查最先进的算法,并讨论这些算法之间的基本差异。调查的一个优点是,我们系统地研究了不同类别的算法底层的理论基础,这提供了深入的见解,以更好地了解网络表示学习领域的发展。
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
神经切线内核(NTK)是分析神经网络及其泛化界限的训练动力学的强大工具。关于NTK的研究已致力于典型的神经网络体系结构,但对于Hadamard产品(NNS-HP)的神经网络不完整,例如StyleGAN和多项式神经网络。在这项工作中,我们为特殊类别的NNS-HP(即多项式神经网络)得出了有限宽度的NTK公式。我们证明了它们与关联的NTK与内核回归预测变量的等效性,该预测扩大了NTK的应用范围。根据我们的结果,我们阐明了针对外推和光谱偏置,PNN在标准神经网络上的分离。我们的两个关键见解是,与标准神经网络相比,PNN能够在外推方案中拟合更复杂的功能,并承认相应NTK的特征值衰减较慢。此外,我们的理论结果可以扩展到其他类型的NNS-HP,从而扩大了我们工作的范围。我们的经验结果验证了更广泛的NNS-HP类别的分离,这为对神经体系结构有了更深入的理解提供了良好的理由。
translated by 谷歌翻译
图形神经网络(GNNS)在节点分类,回归和推荐任务中取得了最新的最新性能。当可提供高质量和丰富的连接结构时,GNNS工作好。但是,在许多真实世界图中,该要求在节点度具有幂律分布的许多真实世界中,因为许多节点具有较少或嘈杂的连接。这种情况的极端情况是节点可能没有邻居,称为严格的冷启动(SCS)场景。这会强制预测模型依赖于节点的输入特征。与通过蒸馏方法相比,我们提出冷啤酒以解决SCS和嘈杂的邻居设置。我们介绍了功能贡献比(FCR),测量使用电感GNN解决SCS问题的可行性,并选择SCS泛化的最佳体系结构。我们通过实验显示FCR Disentangles图数据集的各种组成部分的贡献,并展示了几个公共基准和专有电子商务数据集上的冷啤酒的优越性。我们方法的源代码可用于:https://github.com/amazon-research/gnn-tail-一致化。
translated by 谷歌翻译
图表学习目的旨在将节点内容与图形结构集成以学习节点/图表示。然而,发现许多现有的图形学习方法在具有高异性级别的数据上不能很好地工作,这是不同类标签之间很大比例的边缘。解决这个问题的最新努力集中在改善消息传递机制上。但是,尚不清楚异质性是否确实会损害图神经网络(GNNS)的性能。关键是要展现一个节点与其直接邻居之间的关系,例如它们是异性还是同质性?从这个角度来看,我们在这里研究了杂质表示在披露连接节点之间的关系之前/之后的杂音表示的作用。特别是,我们提出了一个端到端框架,该框架既学习边缘的类型(即异性/同质性),并利用边缘类型的信息来提高图形神经网络的表现力。我们以两种不同的方式实施此框架。具体而言,为了避免通过异质边缘传递的消息,我们可以通过删除边缘分类器鉴定的异性边缘来优化图形结构。另外,可以利用有关异性邻居的存在的信息进行特征学习,因此,设计了一种混合消息传递方法来汇总同质性邻居,并根据边缘分类使异性邻居多样化。广泛的实验表明,在整个同质级别的多个数据集上,通过在多个数据集上提出的框架对GNN的绩效提高了显着提高。
translated by 谷歌翻译