Optimization of directed acyclic graph (DAG) structures has many applications, such as neural architecture search (NAS) and probabilistic graphical model learning. Encoding DAGs into real vectors is a dominant component in most neural-network-based DAG optimization frameworks. Currently, most DAG encoders use an asynchronous message passing scheme which sequentially processes nodes according to the dependency between nodes in a DAG. That is, a node must not be processed until all its predecessors are processed. As a result, they are inherently not parallelizable. In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel. We demonstrate the superiority of PACE through encoder-dependent optimization subroutines that search the optimal DAG structure based on the learned DAG embeddings. Experiments show that PACE not only improves the effectiveness over previous sequential DAG encoders with a significantly boosted training and inference speed, but also generates smooth latent (DAG encoding) spaces that are beneficial to downstream optimization subroutines. Our source code is available at \url{https://github.com/zehao-dong/PACE}
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
The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared to mainstream GNN variants. Therefore, it remains a mystery how Transformers could perform well for graph representation learning. In this paper, we solve this mystery by presenting Graphormer, which is built upon the standard Transformer architecture, and could attain excellent results on a broad range of graph representation learning tasks, especially on the recent OGB Large-Scale Challenge. Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model. To this end, we propose several simple yet effective structural encoding methods to help Graphormer better model graph-structured data. Besides, we mathematically characterize the expressive power of Graphormer and exhibit that with our ways of encoding the structural information of graphs, many popular GNN variants could be covered as the special cases of Graphormer. The code and models of Graphormer will be made publicly available at https://github.com/Microsoft/Graphormer.
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
变压器架构最近在图表表示学习中引起了人们的注意,因为它自然地克服了图神经网络(GNN)的几个局限性,避免了它们严格的结构电感偏置,而仅通过位置编码来编码图形结构。在这里,我们表明,具有位置编码的变压器生成的节点表示不一定捕获它们之间的结构相似性。为了解决这个问题,我们提出了结构感知的变压器,这是一类简单而灵活的图形变压器,建立在新的自我发项机制的基础上。这一新的自我注意力通过在计算注意力之前提取植根于每个节点的子图表来结合结构信息。我们提出了几种自动生成子图表表示的方法,并从理论上说明结果表示至少与子图表一样表现力。从经验上讲,我们的方法在五个图预测基准上实现了最先进的性能。我们的结构感知框架可以利用任何现有的GNN提取子图表表示,我们表明它系统地改善了相对于基本GNN模型的性能,成功地结合了GNN和变形金刚的优势。我们的代码可在https://github.com/borgwardtlab/sat上找到。
translated by 谷歌翻译
基于变压器的模型已在各个领域(例如自然语言处理和计算机视觉)中广泛使用并实现了最先进的性能。最近的作品表明,变压器也可以推广到图形结构化数据。然而,由于技术挑战,诸如节点数量和非本地聚集的技术挑战之类的技术挑战,因此成功限于小规模图,这通常会导致对常规图神经网络的概括性能。在本文中,为了解决这些问题,我们提出了可变形的图形变压器(DGT),以动态采样的键和值对进行稀疏注意。具体而言,我们的框架首先构建具有各种标准的多个节点序列,以考虑结构和语义接近。然后,将稀疏的注意力应用于节点序列,以减少计算成本,以学习节点表示。我们还设计简单有效的位置编码,以捕获节点之间的结构相似性和距离。实验表明,我们的新型图形变压器始终胜过现有的基于变压器的模型,并且与8个图形基准数据集(包括大型图形)的最新模型相比,与最新的模型相比表现出竞争性能。
translated by 谷歌翻译
近年来,图形变压器在各种图形学习任务上表现出了优势。但是,现有图形变压器的复杂性与节点的数量二次缩放,因此难以扩展到具有数千个节点的图形。为此,我们提出了一个邻域聚集图变压器(Nagphormer),该变压器可扩展到具有数百万节点的大图。在将节点特征馈送到变压器模型中之前,Nagphormer构造令牌由称为Hop2Token的邻域聚合模块为每个节点。对于每个节点,Hop2token聚合从每个跳跃到表示形式的邻域特征,从而产生一系列令牌向量。随后,不同HOP信息的结果序列是变压器模型的输入。通过将每个节点视为一个序列,可以以迷你批量的方式训练Nagphormer,从而可以扩展到大图。 Nagphormer进一步开发了基于注意力的读数功能,以便学习每个跳跃的重要性。我们在各种流行的基准测试中进行了广泛的实验,包括六个小数据集和三个大数据集。结果表明,Nagphormer始终优于现有的图形变压器和主流图神经网络。
translated by 谷歌翻译
Graph Neural Networks (GNNs) have shown great potential in the field of graph representation learning. Standard GNNs define a local message-passing mechanism which propagates information over the whole graph domain by stacking multiple layers. This paradigm suffers from two major limitations, over-squashing and poor long-range dependencies, that can be solved using global attention but significantly increases the computational cost to quadratic complexity. In this work, we propose an alternative approach to overcome these structural limitations by leveraging the ViT/MLP-Mixer architectures introduced in computer vision. We introduce a new class of GNNs, called Graph MLP-Mixer, that holds three key properties. First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on the Long Range Graph Benchmark (LRGB) and the TreeNeighbourMatch datasets. Second, they offer better speed and memory efficiency with a complexity linear to the number of nodes and edges, surpassing the related Graph Transformer and expressive GNN models. Third, they show high expressivity in terms of graph isomorphism as they can distinguish at least 3-WL non-isomorphic graphs. We test our architecture on 4 simulated datasets and 7 real-world benchmarks, and show highly competitive results on all of them.
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
变压器架构已成为许多域中的主导选择,例如自然语言处理和计算机视觉。然而,与主流GNN变体相比,它对图形水平预测的流行排行榜没有竞争表现。因此,它仍然是一个谜,变形金机如何对图形表示学习表现良好。在本文中,我们通过提出了基于标准变压器架构构建的Gragemer来解决这一神秘性,并且可以在广泛的图形表示学习任务中获得优异的结果,特别是在最近的OGB大规模挑战上。我们在图中利用变压器的关键洞察是有效地将图形的结构信息有效地编码到模型中。为此,我们提出了几种简单但有效的结构编码方法,以帮助Gramemormer更好的模型图形结构数据。此外,我们在数学上表征了Gramemormer的表现力,并展示了我们编码图形结构信息的方式,许多流行的GNN变体都可以被涵盖为GrameRormer的特殊情况。
translated by 谷歌翻译
代码搜索目标是根据自然语言查询检索相关的代码片段,以提高软件生产力和质量。但是,由于源代码和查询之间的语义间隙,自动代码搜索是具有挑战性的。大多数现有方法主要考虑嵌入的顺序信息,其中文本背后的结构信息不完全考虑。在本文中,我们设计了一个名为GraphsearchNet的新型神经网络框架,通过共同学习源代码和查询的富集语义来启用有效和准确的源代码搜索。具体地,我们建议将源代码和查询编码为两个图,其中双向GGNN以捕获图表的本地结构信息。此外,我们通过利用有效的多主题来增强BigGNN,以补充BigGNN错过的全球依赖。关于Java和Python数据集的广泛实验说明了GraphSearchNet优于当前最先进的工作原位。
translated by 谷歌翻译
在本文中,我们试图通过引入深度学习模型的句法归纳偏见来建立两所学校之间的联系。我们提出了两个归纳偏见的家族,一个家庭用于选区结构,另一个用于依赖性结构。选区归纳偏见鼓励深度学习模型使用不同的单位(或神经元)分别处理长期和短期信息。这种分离为深度学习模型提供了一种方法,可以从顺序输入中构建潜在的层次表示形式,即更高级别的表示由高级表示形式组成,并且可以分解为一系列低级表示。例如,在不了解地面实际结构的情况下,我们提出的模型学会通过根据其句法结构组成变量和运算符的表示来处理逻辑表达。另一方面,依赖归纳偏置鼓励模型在输入序列中找到实体之间的潜在关系。对于自然语言,潜在关系通常被建模为一个定向依赖图,其中一个单词恰好具有一个父节点和零或几个孩子的节点。将此约束应用于类似变压器的模型之后,我们发现该模型能够诱导接近人类专家注释的有向图,并且在不同任务上也优于标准变压器模型。我们认为,这些实验结果为深度学习模型的未来发展展示了一个有趣的选择。
translated by 谷歌翻译
AMR到文本是NLP社区中旨在从抽象含义表示(AMR)图生成句子的关键技术之一。自2013年提出AMR以来,有关AMR到文本的研究越来越普遍,因为AMR作为自然语言的高级语义描述,由于AMR具有独特的优势,因此作为结构化数据的重要分支变得越来越普遍。在本文中,我们简要介绍了AMR到文本。首先,我们介绍了此技术的当前情况,并指出了它的困难。其次,根据先前研究中使用的方法,我们根据它们各自的机制将它们大致分为五个类别和预先训练的语言模型(PLM)。特别是,我们详细介绍了基于神经网络的方法,并介绍了AMR到文本的最新进展,该方法指的是AMR重建,解码器优化等。此外,我们介绍了AMR-TOXT的基准和评估方法。最终,我们提供了当前技术和未来研究的前景的摘要。
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
学习有效的蛋白质表示在生物学的各种任务中至关重要,例如预测蛋白质功能或结构。现有的方法通常在大量未标记的氨基酸序列上预先蛋白质语言模型,然后在下游任务中使用一些标记的数据来对模型进行修复。尽管基于序列的方法具有有效性,但尚未探索蛋白质性能预测的已知蛋白质结构的预处理功能,尽管蛋白质结构已知是蛋白质功能的决定因素,但尚未探索。在本文中,我们建议根据其3D结构预处理蛋白质。我们首先提出一个简单而有效的编码器,以学习蛋白质的几何特征。我们通过利用多视图对比学习和不同的自我预测任务来预先蛋白质图编码器。对功能预测和折叠分类任务的实验结果表明,我们提出的预处理方法表现优于或与最新的基于最新的序列方法相提并论,同时使用较少的数据。我们的实施可在https://github.com/deepgraphlearning/gearnet上获得。
translated by 谷歌翻译
多模式的机器学习已被广​​泛研究以开发通用智能。最近,感知者和感知者IO出色的多模式算法对各种数据集域和任务显示了竞争结果。但是,最近的作品,感知者和感知者IO专注于异质模式,包括图像,文本和语音,并且对于图形结构化数据集的研究作品很少。图是最概括的数据集结构之一,我们可以代表其他数据集,包括图像,文本和语音作为图形结构化数据。图具有与其他数据集域(例如文本和图像)不同的邻接矩阵,并且处理拓扑信息,关系信息和规范的位置信息并不微不足道。在这项研究中,我们提供了图形感知器IO,即图形结构化数据集的感知器IO。我们将图形感知器IO的主要结构保留为感知器IO,因为除了图形结构化数据集外,感知器IO已经很好地处理了各种数据集。图形感知器IO是一种通用方法,它可以处理各种数据集,例如图形结构化数据以及文本和图像。比较图形神经网络,图感知器IO需要较低的复杂性,并且可以有效地合并局部和全局信息。我们表明,图形感知器IO显示了与图形相关任务的各种竞争结果,包括节点分类,图形分类和链接预测。
translated by 谷歌翻译
许多实际关系系统,如社交网络和生物系统,包含动态相互作用。在学习动态图形表示时,必须采用连续的时间信息和几何结构。主流工作通过消息传递网络(例如,GCN,GAT)实现拓扑嵌入。另一方面,时间演进通常通过在栅极机构中具有方便信息过滤的存储单元(例如,LSTM或GU)来表达。但是,由于过度复杂的编码,这种设计可以防止大规模的输入序列。这项工作从自我关注的哲学中学习,并提出了一种高效的基于频谱的神经单元,采用信息的远程时间交互。发达的频谱窗口单元(SWINIT)模型预测了具有保证效率的可扩展动态图形。该架构与一些构成随机SVD,MLP和图形帧卷积的一些简单的有效计算块组装。 SVD加MLP模块编码动态图事件的长期特征演进。帧卷积中的快速帧图形变换嵌入了结构动态。两种策略都提高了模型对可扩展分析的能力。特别地,迭代的SVD近似度将注意力的计算复杂性缩小到具有n个边缘和D边缘特征的动态图形的关注的计算复杂性,并且帧卷积的多尺度变换允许在网络训练中具有足够的可扩展性。我们的Swinit在各种在线连续时间动态图表学习任务中实现了最先进的性能,而与基线方法相比,可学习参数的数量可达七倍。
translated by 谷歌翻译
时间图代表实体之间的动态关系,并发生在许多现实生活中的应用中,例如社交网络,电子商务,通信,道路网络,生物系统等。他们需要根据其生成建模和表示学习的研究超出与静态图有关的研究。在这项调查中,我们全面回顾了近期针对处理时间图提出的神经时间依赖图表的学习和生成建模方法。最后,我们确定了现有方法的弱点,并讨论了我们最近发表的论文提格的研究建议[24]。
translated by 谷歌翻译
Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here we propose Position-aware Graph Neural Networks (P-GNNs), a new class of GNNs for computing position-aware node embeddings. P-GNN first samples sets of anchor nodes, computes the distance of a given target node to each anchor-set, and then learns a non-linear distance-weighted aggregation scheme over the anchor-sets. This way P-GNNs can capture positions/locations of nodes with respect to the anchor nodes. P-GNNs have several advantages: they are inductive, scalable, and can incorporate node feature information. We apply P-GNNs to multiple prediction tasks including link prediction and community detection. We show that P-GNNs consistently outperform state of the art GNNs, with up to 66% improvement in terms of the ROC AUC score.Node embedding methods can be categorized into Graph Neural Networks (GNNs) approaches (Scarselli et al., 2009),
translated by 谷歌翻译
与自然语言相反,源代码理解受到令牌之间的语法关系的影响,无论其标识符名称如何。源代码的图表表示诸如抽象语法树(AST)可以从源代码中捕获不明显的令牌之间的关系。我们提出了一种新颖的方法,GN变压器在融合序列和图形模型上学习端到端我们调用语法代码图(SCG)。 GN变压器使用自我关注机制在图形网络(GN)框架上展开。 SCG是源代码片段和AST表示之间的早期融合的结果。我们对SCG的结构进行了实验,对模型设计的消融研究,以及结论性能优势来自融合表示的超参数。所提出的方法在两个代码摘要数据集中实现最先进的性能,并跨越三个自动编码摘要度量(BLEU,Meteor,Rouge-L)。我们进一步评估了我们模型的人类感知质量和以前的工作与专家用户学习。我们的模型以人类的质量和准确性高出现有技术。
translated by 谷歌翻译