给定图表具有部分观察到节点特征,我们如何准确估计缺失功能?特征估计是分析现实图表的关键问题,其特征在数据收集过程中通常缺少。准确的估计不仅提供了节点的多种信息,而且还支持需要全面观察节点特征的图形神经网络的推断。但是,设计一种估计高维特征的有效方法是具有挑战性的,因为它要求估算器具有较大的表示能力,从而增加过度拟合的风险。在这项工作中,我们提出了SVGA(结构化变分图自动编码器),这是一种精确的特征估计方法。 SVGA通过结构化变异推断将强固体化应用于潜在变量的分布,该变量推断将变量的先前作为基于图结构的高斯马尔可夫随机字段建模。结果,SVGA结合了概率推理和图形神经网络的优势,在实际数据集中实现了最新性能。
translated by 谷歌翻译
在本文中,我们研究了在非全粒图上进行节点表示学习的自我监督学习的问题。现有的自我监督学习方法通​​常假定该图是同质的,其中链接的节点通常属于同一类或具有相似的特征。但是,这种同质性的假设在现实图表中并不总是正确的。我们通过为图神经网络开发脱钩的自我监督学习(DSSL)框架来解决这个问题。 DSSL模仿了节点的生成过程和语义结构的潜在变量建模的链接,该过程将不同邻域之间的不同基础语义解散到自我监督的节点学习过程中。我们的DSSL框架对编码器不可知,不需要预制的增强,因此对不同的图表灵活。为了通过潜在变量有效地优化框架,我们得出了自我监督目标的较低范围的证据,并开发了具有变异推理的可扩展培训算法。我们提供理论分析,以证明DSSL享有更好的下游性能。与竞争性的自我监督学习基线相比,对各种类图基准的广泛实验表明,我们提出的框架可以显着取得更好的性能。
translated by 谷歌翻译
Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node attributes in VGAEs and show that attribute decoding is important for node representation learning. We further propose a new learning model, interpretable NOde Representation with Attribute Decoding (NORAD). The model encodes node representations in an interpretable approach: node representations capture community structures in the graph and the relationship between communities and node attributes. We further propose a rectifying procedure to refine node representations of isolated notes, improving the quality of these nodes' representations. Our empirical results demonstrate the advantage of the proposed model when learning graph data in an interpretable approach.
translated by 谷歌翻译
数据增强已广泛用于图像数据和语言数据,但仍然探索图形神经网络(GNN)。现有方法专注于从全局视角增强图表数据,并大大属于两个类型:具有特征噪声注入的结构操纵和对抗训练。但是,最近的图表数据增强方法忽略了GNNS“消息传递机制的本地信息的重要性。在这项工作中,我们介绍了本地增强,这通过其子图结构增强了节点表示的局部。具体而言,我们将数据增强模拟为特征生成过程。鉴于节点的功能,我们的本地增强方法了解其邻居功能的条件分布,并生成更多邻居功能,以提高下游任务的性能。基于本地增强,我们进一步设计了一个新颖的框架:La-GNN,可以以即插即用的方式应用于任何GNN模型。广泛的实验和分析表明,局部增强一致地对各种基准的各种GNN架构始终如一地产生性能改进。
translated by 谷歌翻译
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance before and after perturbation can enhance human interpretation. Most existing studies on counterfactual explanations are limited in tabular data or image data. In this work, we study the problem of counterfactual explanation generation on graphs. A few studies have explored counterfactual explanations on graphs, but many challenges of this problem are still not well-addressed: 1) optimizing in the discrete and disorganized space of graphs; 2) generalizing on unseen graphs; and 3) maintaining the causality in the generated counterfactuals without prior knowledge of the causal model. To tackle these challenges, we propose a novel framework CLEAR which aims to generate counterfactual explanations on graphs for graph-level prediction models. Specifically, CLEAR leverages a graph variational autoencoder based mechanism to facilitate its optimization and generalization, and promotes causality by leveraging an auxiliary variable to better identify the underlying causal model. Extensive experiments on both synthetic and real-world graphs validate the superiority of CLEAR over the state-of-the-art methods in different aspects.
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
图形神经网络(GNNS)在提供图形结构时良好工作。但是,这种结构可能并不总是在现实世界应用中可用。该问题的一个解决方案是推断任务特定的潜在结构,然后将GNN应用于推断的图形。不幸的是,可能的图形结构的空间与节点的数量超级呈指数,因此任务特定的监督可能不足以学习结构和GNN参数。在这项工作中,我们提出了具有自我监督或拍打的邻接和GNN参数的同时学习,这是通过自我监督来推断图形结构的更多监督的方法。一个综合实验研究表明,缩小到具有数十万个节点的大图和胜过了几种模型,以便在已建立的基准上学习特定于任务的图形结构。
translated by 谷歌翻译
Graph AutoCododers(GAE)和变分图自动编码器(VGAE)作为链接预测的强大方法出现。他们的表现对社区探测问题的印象不那么令人印象深刻,根据最近和同意的实验评估,它们的表现通常超过了诸如louvain方法之类的简单替代方案。目前尚不清楚可以通过GAE和VGAE改善社区检测的程度,尤其是在没有节点功能的情况下。此外,不确定是否可以在链接预测上同时保留良好的性能。在本文中,我们表明,可以高精度地共同解决这两个任务。为此,我们介绍和理论上研究了一个社区保留的消息传递方案,通过在计算嵌入空间时考虑初始图形结构和基于模块化的先验社区来掺杂我们的GAE和VGAE编码器。我们还提出了新颖的培训和优化策略,包括引入一个模块化的正规器,以补充联合链路预测和社区检测的现有重建损失。我们通过对各种现实世界图的深入实验验证,证明了方法的经验有效性,称为模块化感知的GAE和VGAE。
translated by 谷歌翻译
由于能够处理一般结构化数据,因此在图形上的机器学习方法在许多应用程序中被证明是有用的。高斯马尔可夫随机字段(GMRF)的框架提供了一种原则性的方法,可以通过利用其稀疏结构来定义图表上的高斯模型。我们为基于深GMRF的多层结构而建立的一般图表提出了一个灵活的GMRF模型,该模型最初仅针对晶格图。通过设计新类型的图层,我们使模型可以扩展到大图。该层的构建是为了使用图形神经网络的变异推理和现有软件框架进行有效的训练。对于高斯的可能性,潜在领域接近确切的贝叶斯推理。这可以通过随附的不确定性估计做出预测。通过对许多合成和现实世界数据集的实验来验证所提出的模型的有用性,在该数据集中,它与其他贝叶斯和深度学习方法进行了比较。
translated by 谷歌翻译
网络嵌入作为网络分析的有希望的研究领域出现。最近,通过将冗余还原原理应用于对应于图像样本的两个扭曲版本的嵌入向量,提出了一种名为Barlow双胞胎的方法。通过此激励,我们提出了Barlow Graph自动编码器,这是一个简单而有效的学习网络嵌入的架构。它旨在最大限度地提高节点的立即和较大邻域的嵌入向量之间的相似性,同时最小化这些投影的组件之间的冗余。此外,我们还介绍了名为Barlow变形图自动编码器的变型对应物。我们的方法产生了对归纳链路预测的有希望的结果,并且还涉及用于聚类和下游节点分类的领域,如广泛的三个基准引用数据集上的多种已知技术的广泛比较所证明的。
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
在现代社交媒体和网络时代,现实世界现象的图表表示已成为我的洞察力的令人难以置信的源泉。通常,我们有兴趣了解图形中的实体如何互连。图形神经网络(GNN)已被证明是在各种图形学习任务中的一个非常有用的工具,包括节点分类,链路预测和边缘分类。但是,在大多数任务中,我们使用的图形数据可能是嘈杂的,并且可能包含虚假边缘。也就是说,与底层图形结构有很多不确定性。最近建模不确定性的方法一直使用贝叶斯框架,并将图表视为随机变量,与模型参数相关的概率。已经显示出介绍基于图形的模型,专门用于半监督节点分类,从而显示出更高的分类精度。然而,在最近的工作中提出的图表推理的方法没有考虑图表的结构。在本文中,我们提出了一种新颖的算法,使用邻域随机步行采样(BGCN-NRW)提出了一种名为贝叶斯图卷积网络的新颖算法,它使用了利用图形结构的Markov链蒙特卡罗(MCMC)的图形采样算法,通过使用变分或推理来减少过度拟合与半监督节点分类中的最先进的技术相比,层,并始终竞争的分类结果。
translated by 谷歌翻译
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.
translated by 谷歌翻译
疾病预测是医学应用中的知名分类问题。 GCNS提供了一个强大的工具,用于分析患者相对于彼此的特征。这可以通过将问题建模作为图形节点分类任务来实现,其中每个节点是患者。由于这种医学数据集的性质,类别不平衡是疾病预测领域的普遍存在问题,其中类的分布是歪曲的。当数据中存在类别不平衡时,现有的基于图形的分类器倾向于偏向于主要类别并忽略小类中的样本。另一方面,所有患者中罕见阳性病例的正确诊断在医疗保健系统中至关重要。在传统方法中,通过将适当的权重分配给丢失函数中的类别来解决这种不平衡,这仍然依赖于对异常值敏感的权重的相对值,并且在某些情况下偏向于小类(ES)。在本文中,我们提出了一种重加权的对抗性图形卷积网络(RA-GCN),以防止基于图形的分类器强调任何特定类的样本。这是通过将基于图形的神经网络与每个类相关联来完成的,这负责加权类样本并改变分类器的每个样本的重要性。因此,分类器自身调节并确定类之间的边界,更加关注重要样本。分类器和加权网络的参数受到侵犯方法训练。我们在合成和三个公共医疗数据集上显示实验。与最近的方法相比,ra-gcn展示了与最近的方法在所有三个数据集上识别患者状态的方法相比。详细分析作为合成数据集的定量和定性实验提供。
translated by 谷歌翻译
我们介绍了一种新颖的屏蔽图AutoEncoder(MGAE)框架,以在图形结构数据上执行有效的学习。从自我监督学习中欣识见,我们随机掩盖了大部分边缘,并在训练期间尝试重建这些缺失的边缘。 Mgae有两个核心设计。首先,我们发现掩蔽了输入图结构的高比率,例如70 \%$,产生一个非凡和有意义的自我监督任务,使下游应用程序受益。其次,我们使用图形神经网络(GNN)作为编码器,以在部分掩蔽的图表上执行消息传播。为了重建大量掩模边缘,提出了一种定制的互相关解码器。它可以捕获多粒度的锚边的头部和尾部节点之间的互相关。耦合这两种设计使MGAE能够有效且有效地培训。在多个开放数据集(Planetoid和OGB基准测试)上进行了广泛的实验,证明MGAE通常比链接预测和节点分类更好地表现优于最先进的无监督竞争对手。
translated by 谷歌翻译
We investigate the representation power of graph neural networks in the semisupervised node classification task under heterophily or low homophily, i.e., in networks where connected nodes may have different class labels and dissimilar features. Many popular GNNs fail to generalize to this setting, and are even outperformed by models that ignore the graph structure (e.g., multilayer perceptrons). Motivated by this limitation, we identify a set of key designs-ego-and neighbor-embedding separation, higher-order neighborhoods, and combination of intermediate representations-that boost learning from the graph structure under heterophily. We combine them into a graph neural network, H 2 GCN, which we use as the base method to empirically evaluate the effectiveness of the identified designs. Going beyond the traditional benchmarks with strong homophily, our empirical analysis shows that the identified designs increase the accuracy of GNNs by up to 40% and 27% over models without them on synthetic and real networks with heterophily, respectively, and yield competitive performance under homophily.
translated by 谷歌翻译
Data-efficient learning on graphs (GEL) is essential in real-world applications. Existing GEL methods focus on learning useful representations for nodes, edges, or entire graphs with ``small'' labeled data. But the problem of data-efficient learning for subgraph prediction has not been explored. The challenges of this problem lie in the following aspects: 1) It is crucial for subgraphs to learn positional features to acquire structural information in the base graph in which they exist. Although the existing subgraph neural network method is capable of learning disentangled position encodings, the overall computational complexity is very high. 2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure. Subgraph augmentation is more susceptible to undesirable perturbations. 3) Only a small number of nodes in the base graph are contained in subgraphs, which leads to a potential ``bias'' problem that the subgraph representation learning is dominated by these ``hot'' nodes. By contrast, the remaining nodes fail to be fully learned, which reduces the generalization ability of subgraph representation learning. In this paper, we aim to address the challenges above and propose a Position-Aware Data-Efficient Learning framework for subgraph neural networks called PADEL. Specifically, we propose a novel node position encoding method that is anchor-free, and design a new generative subgraph augmentation method based on a diffused variational subgraph autoencoder, and we propose exploratory and exploitable views for subgraph contrastive learning. Extensive experiment results on three real-world datasets show the superiority of our proposed method over state-of-the-art baselines.
translated by 谷歌翻译
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Although there are several defense methods to improve GNN robustness by eliminating adversarial components, they may also impair the underlying clean graph structure that contributes to GNN training. In addition, few of those defense models can scale to large graphs due to their high computational complexity and memory usage. In this paper, we propose GARNET, a scalable spectral method to boost the adversarial robustness of GNN models. GARNET first leverages weighted spectral embedding to construct a base graph, which is not only resistant to adversarial attacks but also contains critical (clean) graph structure for GNN training. Next, GARNET further refines the base graph by pruning additional uncritical edges based on probabilistic graphical model. GARNET has been evaluated on various datasets, including a large graph with millions of nodes. Our extensive experiment results show that GARNET achieves adversarial accuracy improvement and runtime speedup over state-of-the-art GNN (defense) models by up to 13.27% and 14.7x, respectively.
translated by 谷歌翻译
图形神经网络(GNNS)在广泛的应用方面显示了有希望的结果。 GNN的大多数实证研究直接将观察图视为输入,假设观察到的结构完美地描绘了节点之间的准确性和完全关系。然而,现实世界中的图形是不可避免的或不完整的,甚至可以加剧图表表示的质量。在这项工作中,我们提出了一种新颖的变分信息瓶颈引导图形结构学习框架,即vib-gsl,在信息理论的角度下。 VIB-GSL推进了图形结构学习的信息瓶颈(IB)原则,为挖掘潜在的任务关系提供了更优雅且普遍的框架。 VIB-GSL了解一个信息和压缩图形结构,用于蒸馏出特定的下游任务的可操作信息。 VIB-GSL为不规则图数据推导了变化近似,以形成促进训练稳定性的易切换IB目标函数。广泛的实验结果表明,VIB-GSL的卓越有效性和鲁棒性。
translated by 谷歌翻译
图表可以模拟实体之间的复杂交互,它在许多重要的应用程序中自然出现。这些应用程序通常可以投入到标准图形学习任务中,其中关键步骤是学习低维图表示。图形神经网络(GNN)目前是嵌入方法中最受欢迎的模型。然而,邻域聚合范例中的标准GNN患有区分\ EMPH {高阶}图形结构的有限辨别力,而不是\ EMPH {低位}结构。为了捕获高阶结构,研究人员求助于主题和开发的基于主题的GNN。然而,现有的基于主基的GNN仍然仍然遭受较少的辨别力的高阶结构。为了克服上述局限性,我们提出了一个新颖的框架,以更好地捕获高阶结构的新框架,铰接于我们所提出的主题冗余最小化操作员和注射主题组合的新颖框架。首先,MGNN生成一组节点表示W.R.T.每个主题。下一阶段是我们在图案中提出的冗余最小化,该主题在彼此相互比较并蒸馏出每个主题的特征。最后,MGNN通过组合来自不同图案的多个表示来执行节点表示的更新。特别地,为了增强鉴别的功率,MGNN利用重新注射功能来组合表示的函数w.r.t.不同的主题。我们进一步表明,我们的拟议体系结构增加了GNN的表现力,具有理论分析。我们展示了MGNN在节点分类和图形分类任务上的七个公共基准上表现出最先进的方法。
translated by 谷歌翻译