光谱群集中使用的目标函数通常由两个术语组成:i)一个术语最小化群集分配的局部二次变化,并且;ii)一个平衡聚类分区并有助于避免退化解决方案的术语。本文表明,配备合适消息传递层的图形神经网络可以通过仅优化平衡项来生成良好的集群分配。归因图数据集的结果显示了拟议方法在聚类性能和计算时间方面的有效性。
translated by 谷歌翻译
Graph Neural Networks (GNNs) are deep learning models designed to process attributed graphs. GNNs can compute cluster assignments accounting both for the vertex features and for the graph topology. Existing GNNs for clustering are trained by optimizing an unsupervised minimum cut objective, which is approximated by a Spectral Clustering (SC) relaxation. SC offers a closed-form solution that, however, is not particularly useful for a GNN trained with gradient descent. Additionally, the SC relaxation is loose and yields overly smooth cluster assignments, which do not separate well the samples. We propose a GNN model that optimizes a tighter relaxation of the minimum cut based on graph total variation (GTV). Our model has two core components: i) a message-passing layer that minimizes the $\ell_1$ distance in the features of adjacent vertices, which is key to achieving sharp cluster transitions; ii) a loss function that minimizes the GTV in the cluster assignments while ensuring balanced partitions. By optimizing the proposed loss, our model can be self-trained to perform clustering. In addition, our clustering procedure can be used to implement graph pooling in deep GNN architectures for graph classification. Experiments show that our model outperforms other GNN-based approaches for clustering and graph pooling.
translated by 谷歌翻译
图形神经网络(GNN)已在许多图分析任务(例如节点分类和链接预测)上实现了最新结果。然而,事实证明,图形群集等图形上的重要无监督问题对GNN的进步具有更大的抵抗力。图群集的总体目标与GNN中的节点合并相同 - 这是否意味着GNN池方法在聚类图上做得很好?令人惊讶的是,答案是没有的 - 当前的GNN合并方法通常无法恢复群集结构,而在简单的基线(例如应用于学习的表示形式上的K-均值)良好工作的情况下。我们通过仔细设计一组实验来进一步研究,以研究图形结构和属性数据中的不同信噪比情景。为了解决这些方法在聚类中的性能不佳,我们引入了深层模块化网络(DMON),这是一种受群集质量模块化量度启发的无监督池方法,并显示了它如何解决现实世界图的挑战性聚类结构的恢复。同样,在现实世界中,我们表明DMON产生的高质量簇与地面真相标签密切相关,从而实现了最先进的结果,比不同指标的其他合并方法提高了40%以上。
translated by 谷歌翻译
Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods are inherently flat and do not learn hierarchical representations of graphs-a limitation that is especially problematic for the task of graph classification, where the goal is to predict the label associated with an entire graph. Here we propose DIFFPOOL, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DIFFPOOL learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer. Our experimental results show that combining existing GNN methods with DIFFPOOL yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark data sets.
translated by 谷歌翻译
In the last few years, graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. This emerging field has witnessed an extensive growth of promising techniques that have been applied with success to computer science, mathematics, biology, physics and chemistry. But for any successful field to become mainstream and reliable, benchmarks must be developed to quantify progress. This led us in March 2020 to release a benchmark framework that i) comprises of a diverse collection of mathematical and real-world graphs, ii) enables fair model comparison with the same parameter budget to identify key architectures, iii) has an open-source, easy-to-use and reproducible code infrastructure, and iv) is flexible for researchers to experiment with new theoretical ideas. As of December 2022, the GitHub repository has reached 2,000 stars and 380 forks, which demonstrates the utility of the proposed open-source framework through the wide usage by the GNN community. In this paper, we present an updated version of our benchmark with a concise presentation of the aforementioned framework characteristics, an additional medium-sized molecular dataset AQSOL, similar to the popular ZINC, but with a real-world measured chemical target, and discuss how this framework can be leveraged to explore new GNN designs and insights. As a proof of value of our benchmark, we study the case of graph positional encoding (PE) in GNNs, which was introduced with this benchmark and has since spurred interest of exploring more powerful PE for Transformers and GNNs in a robust experimental setting.
translated by 谷歌翻译
Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of generalizing the convolution operation to graphs has been proven to improve performance and is widely used. However, the method of applying downsampling to graphs is still difficult to perform and has room for improvement. In this paper, we propose a graph pooling method based on selfattention. Self-attention using graph convolution allows our pooling method to consider both node features and graph topology. To ensure a fair comparison, the same training procedures and model architectures were used for the existing pooling methods and our method. The experimental results demonstrate that our method achieves superior graph classification performance on the benchmark datasets using a reasonable number of parameters.
translated by 谷歌翻译
Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Some existing approaches extract deep features from pre-trained networks and build a graph to apply classical clustering methods (e.g., $k$-means and normalized-cuts) as a post-processing stage. These techniques reduce the high-dimensional information encoded in the features to pair-wise scalar affinities. In this work, we replace classical clustering algorithms with a lightweight Graph Neural Network (GNN) trained to achieve the same clustering objective function. However, in contrast to existing approaches, we feed the GNN not only the pair-wise affinities between local image features but also the raw features themselves. Maintaining this connection between the raw feature and the clustering goal allows to perform part semantic segmentation implicitly, without requiring additional post-processing steps. We demonstrate how classical clustering objectives can be formulated as self-supervised loss functions for training our image segmentation GNN. Additionally, we use the Correlation-Clustering (CC) objective to perform clustering without defining the number of clusters ($k$-less clustering). We apply the proposed method for object localization, segmentation, and semantic part segmentation tasks, surpassing state-of-the-art performance on multiple benchmarks.
translated by 谷歌翻译
在过去的几年中,已经开发了图形绘图技术,目的是生成美学上令人愉悦的节点链接布局。最近,利用可区分损失功能的使用已为大量使用梯度下降和相关优化算法铺平了道路。在本文中,我们提出了一个用于开发图神经抽屉(GND)的新框架,即依靠神经计算来构建有效且复杂的图的机器。 GND是图形神经网络(GNN),其学习过程可以由任何提供的损失函数(例如图形图中通常使用的损失函数)驱动。此外,我们证明,该机制可以由通过前馈神经网络计算的损失函数来指导,并根据表达美容特性的监督提示,例如交叉边缘的最小化。在这种情况下,我们表明GNN可以通过位置功能很好地丰富与未标记的顶点处理。我们通过为边缘交叉构建损失函数来提供概念验证,并在提议的框架下工作的不同GNN模型之间提供定量和定性的比较。
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(GNN)已被证明可以实现竞争结果,以解决与图形相关的任务,例如节点和图形分类,链接预测和节点以及各种域中的图形群集。大多数GNN使用消息传递框架,因此称为MPNN。尽管有很有希望的结果,但据报道,MPNN会遭受过度平滑,过度阵型和不足的影响。文献中已经提出了图形重新布线和图形池作为解决这些局限性的解决方案。但是,大多数最先进的图形重新布线方法无法保留该图的全局拓扑,因此没有可区分(电感),并且需要调整超参数。在本文中,我们提出了Diffwire,这是一个在MPNN中进行图形重新布线的新型框架,它通过利用LOV \'ASZ绑定来原理,完全可区分且无参数。我们的方法通过提出两个新的,mpnns中的新的互补层来提供统一的图形重新布线:首先,ctlayer,一个学习通勤时间并将其用作边缘重新加权的相关函数;其次,Gaplayer是优化光谱差距的图层,具体取决于网络的性质和手头的任务。我们从经验上验证了我们提出的方法的价值,并使用基准数据集分别验证了这些层的每个层以进行图形分类。 Diffwire将通勤时间的可学习性汇集到相关的曲率定义,为发展更具表现力的MPNN的发展打开了大门。
translated by 谷歌翻译
最近的图表聚类方法采用了图形自动编码器(GAES)来执行联合聚类和嵌入学习。但是,两个关键问题被忽视了。首先,通过使用嘈杂的聚类分配学习造成的累积误差降低了聚类模型的有效性和鲁棒性。此问题称为随机性。其次,重建邻接矩阵设置模型以学习聚类任务的无关相似之处。此问题称为特征漂移。有趣的是,上述问题之间的理论关系尚未调查。我们从两个方面研究这些问题:(1)当在同一级别进行聚类和重建时,特征随机性和特征漂移之间存在权衡,并且(2)GAE模型的特征漂移问题更为显着,与Vanilla自动编码器模型相比,由于图形卷积操作和图形解码设计。这些发现的动机,我们重构了基于GAE的聚类方法。我们的解决方案是两倍。首先,我们提出了一种采样操作员$ \ xi $,它触发了对嘈杂聚类分配的保护机制。其次,我们提出了一种运营商$ \ Upsilon $,它通过逐渐将重建的图形转换为群集导向的一个来触发校正机制。作为主要优势,我们的解决方案授予聚类有效性和稳健性的相当大提高,并且可以很容易地对现有的GAE模型进行定制。
translated by 谷歌翻译
Many real-world systems can be represented as graphs where the different entities are presented by nodes and their interactions by edges. An important task in studying large datasets is graph clustering. While there has been a lot of work on graph clustering using the connectivity between the nodes, many real-world networks also have node attributes. Clustering attributed graphs requires joint modeling of graph structure and node attributes. Recent work has focused on graph convolutional networks and graph convolutional filters to combine structural and content information. However, these methods are mostly limited to lowpass filtering and do not explicitly optimize the filters for the clustering task. In this paper, we introduce a graph signal processing based approach, where we design polynomial graph filters optimized for clustering. The proposed approach is formulated as a two-step iterative optimization problem where graph filters that are interpretable and optimal for the given data are learned while maximizing the separation between different clusters. The proposed approach is evaluated on attributed networks and compared to the state-of-the-art graph convolutional network approaches.
translated by 谷歌翻译
随着各个领域的深度学习的巨大成功,图形神经网络(GNNS)也成为图形分类的主要方法。通过全局读出操作,只会聚合所有节点(或节点群集)表示,现有的GNN分类器获得输入图的图级表示,并使用表示来预测其类标签。但是,这种全局聚合不考虑每个节点的结构信息,这导致全局结构的信息丢失。特别地,它通过对所有节点表示来强制执行分类器的相同权重参数来限制辨别力;在实践中,他们中的每一个都有助于不同于其结构语义的目标类别。在这项工作中,我们提出了结构性语义读数(SSREAD)来总结位置级节点表示,这允许为分类模拟特定位置的权重参数,以及有效地捕获与全局结构相关的图形语义。给定输入图,SSREAD旨在通过使用其节点与结构原型之间的语义对齐来识别结构上有意义的位置,该结构原型编码每个位置的原型特征。结构原型经过优化,以最小化所有训练图的对准成本,而其他GNN参数训练以预测类标签。我们的实验结果表明,SSREAD显着提高了GNN分类器的分类性能和可解释性,同时兼容各种聚合函数,GNN架构和学习框架。
translated by 谷歌翻译
由于其数值益处增加及其坚实的数学背景,光谱聚类方法的非线性重构近来的关注。我们在$ p $ -norm中提出了一种新的直接多道谱聚类算法,以$ p \ in(1,2] $。计算图表的多个特征向量的问题$ p $ -laplacian,标准的非线性概括Graph Laplacian,被重用作为Grassmann歧管的无约束最小化问题。$ P $的价值以伪连续的方式减少,促进对应于最佳图形的稀疏解决方案载体作为$ P $接近。监测单调减少平衡图削减了我们从$ P $ -Levels获得的最佳可用解决方案的保证。我们展示了我们算法在各种人工测试案件中的算法的有效性和准确性。我们的数值和比较结果具有各种状态-Art聚类方法表明,所提出的方法在均衡的图形剪切度量和标签分配的准确性方面取得高质量的集群。此外,我们进行S面部图像和手写字符分类的束缚,以展示现实数据集中的适用性。
translated by 谷歌翻译
基于图形的群集在群集任务中扮演着重要作用。作为图形卷积网络(GCN),图形类型数据上的神经网络的变体已经实现了令人印象深刻的性能,发现GCN是否可用于在非图形数据上增加基于图形的聚类方法,即,一般数据。但是,鉴于$ N $示例,基于图形的聚类方法通常需要至少$ O(n ^ 2)$时间来构建图形,图表卷积需要密集图和$ uyn $ o(n ^ 2)$。 o(| \ mathcal {e} |)$ for稀疏的$ | \ mathcal {e} | $边。换句话说,基于图形的聚类和GCN患有严重的低效率问题。为了解决这个问题,进一步雇用GCN促进基于图形的聚类的能力,我们提出了一种新的聚类方法,奇迹。由于常规群集方案中未提供图形结构,首先通过引入生成图模型来展示如何将非图形数据集转换为图形,该模型用于构建GCN。从原始数据生成锚来构建二分的图形,使得图表卷积的计算复杂度从$ O(n ^ 2)$和$ o(| \ mathcal {e} |)$到$ o(n) $。群集的后续步骤可以轻松设计为$ O(n)$操作。有趣的是,锚天然导致暹罗的GCN架构。由锚构造的二分图是动态更新的,以利用数据后面的高级信息。最终,我们理论上证明简单的更新将导致退化,因此设计了特定的策略。
translated by 谷歌翻译
我们提出了一种基于图形神经网络(GNN)的端到端框架,以平衡通用网格中的功率流。优化被帧为监督的顶点回归任务,其中GNN培训以预测每个网格分支的电流和功率注入,从而产生功率流量平衡。通过将电网表示为与顶点的分支的线图,我们可以培训一个更准确和强大的GNN来改变底层拓扑。此外,通过使用专门的GNN层,我们能够构建一个非常深的架构,该架构占图表上的大街区,同时仅实现本地化操作。我们执行三个不同的实验来评估:i)使用深入GNN模型时使用本地化而不是全球运营的好处和趋势; ii)图形拓扑中对扰动的弹性;和iii)能力同时在多个网格拓扑上同时培训模型以及新的看不见网格的概括性的改进。拟议的框架是有效的,而且与基于深度学习的其他求解器相比,不仅对网格组件上的物理量而且对拓扑的物理量具有鲁棒性。
translated by 谷歌翻译
图形神经网络(GNNS)可以使用深度学习对图进行分析,并在图中捕获结构化信息的结果有希望的结果。本文着重于创建一个小图来表示原始图,以便在尺寸降低的图上训练的GNN可以做出准确的预测。我们将原始图视为接收场的分布,并旨在合成一个小图,其接受场具有相似的分布。因此,我们通过接受场分布匹配(GCDM)提出了图形屈服,该图是通过使用最大平均差异(MMD)量化的分布匹配损耗来优化合成图来完成的。此外,我们证明了GCDM生成的合成图在评估阶段高度概括为各种模型,并且使用此框架可显着提高冷凝速度。
translated by 谷歌翻译
在本文中,我们提出了多分辨率的等级图变分性Autiachoders(MGVAE),第一层级生成模型以多分辨率和等分的方式学习和生成图。在每个分辨率级别,MGVAE采用更高的顺序消息,以便在学习中对图进行编码,同时学习将其分配到互斥的集群中并赋予最终产生潜在分布的层次结构的较低分辨率。然后,MGVAE构造分层生成模型以改变地解码成粗糙的图形的层次。重要的是,我们提出的框架是关于节点排序的端到端排列等级。MGVAE通过多种生成任务实现竞争结果,包括一般图生成,分子产生,无监督的分子表示学习,以预测分子特性,引用图的链路预测,以及基于图的图像生成。
translated by 谷歌翻译
我们提出了一种基于图形神经网络的图分算法。对于图表中的每个节点,网络输出每个分区的概率。图形神经网络由两个模块组成:嵌入阶段和分区阶段。首先通过最小化由光谱图理论的启发的损耗函数来训练嵌入阶段。分区模块通过损耗函数培训,该损耗函数对应于归一化切割的预期值。神经网络的两部分依赖于Sage卷积层和粗糙化粗糙匹配的图表。神经网络的多级结构受到多重级算法的启发。我们的方法概括了更大的图表,并且与Metis,Scotch和光谱分区相当的分区质量,与Metis和光谱分区相比具有较短的运行时。
translated by 谷歌翻译
Machine Unerning是在收到删除请求时从机器学习(ML)模型中删除某些培训数据的影响的过程。虽然直接而合法,但从划痕中重新训练ML模型会导致高计算开销。为了解决这个问题,在图像和文本数据的域中提出了许多近似算法,其中SISA是最新的解决方案。它将训练集随机分配到多个碎片中,并为每个碎片训练一个组成模型。但是,将SISA直接应用于图形数据可能会严重损害图形结构信息,从而导致的ML模型实用程序。在本文中,我们提出了Grapheraser,这是一种针对图形数据量身定制的新型机器学习框架。它的贡献包括两种新型的图形分区算法和一种基于学习的聚合方法。我们在五个现实世界图数据集上进行了广泛的实验,以说明Grapheraser的学习效率和模型实用程序。它可以实现2.06 $ \ times $(小数据集)至35.94 $ \ times $(大数据集)未学习时间的改进。另一方面,Grapheraser的实现最高62.5美元\%$更高的F1分数,我们提出的基于学习的聚合方法可达到高达$ 112 \%$ $ F1分数。 github.com/minchen00/graph-unlearning}。}。}
translated by 谷歌翻译