灵感来自最近应用于图像上的自我监督方法的成功,图形结构数据的自我监督学习已经看到迅速增长,特别是基于增强的对比方法。但是,我们认为没有精心设计的增强技术,图形上的增强可能是任意行为的,因为图形的底层语义可以急剧地改变。因此,现有增强的方法的性能高度依赖于增强方案的选择,即与增强相关联的超级参数。在本文中,我们提出了一种名为AFGRL的图表的一种新的增强自我监督学习框架。具体地,我们通过发现与图形共享本地结构信息和全局语义的节点来生成图表的替代视图。各种数据集的各种节点级任务,即节点分类,群集和相似性搜索的广泛实验证明了AFGRL的优越性。 AFGRL的源代码可在https://github.com/namkyeong/afgrl中获得。
translated by 谷歌翻译
在过去的几年中,图表学习(GRL)是分析图形结构数据的有力策略。最近,GRL方法通过采用用于图像的学习表示形式而开发的自我监督学习方法来显示出令人鼓舞的结果。尽管它们成功了,但现有的GRL方法倾向于忽略图像和图形之间的固有区别,即,假定图像是独立和相同分布的,而图表在数据实例之间显示了关系信息,即节点。为了完全受益于图形结构数据中固有的关系信息,我们提出了一种名为RGRL的新颖GRL方法,该方法从图形本身生成的关系信息中学习。 RGRL学习节点表示形式,使节点之间的关系是增强的不变性,即增强不变的关系,只要保留节点之间的关系,就可以改变节点表示。通过在全球和本地观点中考虑节点之间的关系,RGRL克服了对对比和非对抗性方法的局限性,并实现了两者中最好的。在各种下游任务上对十四个基准数据集进行了广泛的实验,证明了RGRL优于最先进的基线。 RGRL的源代码可在https://github.com/namkyeong/rgrl上获得。
translated by 谷歌翻译
图对比度学习(GCL)一直是图形自学学习的新兴解决方案。 GCL的核心原理是在正视图中降低样品之间的距离,但在负视图中增加样品之间的距离。在实现有希望的性能的同时,当前的GCL方法仍然受到两个局限性:(1)增强的不可控制的有效性,该图扰动可能会产生针对语义和图形数据的特征流程的无效视图; (2)不可靠的二进制对比理由,对于非欧几里得图数据而言,难以确定构造观点的积极性和负面性。为了应对上述局限性,我们提出了一个新的对比度学习范式,即图形软对比度学习(GSCL),该范例通过排名的社区无需任何增强和二进制对比符合性,在较细性的范围内进行对比度学习。 GSCL建立在图接近的基本假设上,即连接的邻居比遥远的节点更相似。具体而言,我们在配对和列表的封闭式排名中,以保留附近的相对排名关系。此外,随着邻里规模的指数增长,考虑了更多的啤酒花,我们提出了提高学习效率的邻里抽样策略。广泛的实验结果表明,我们提出的GSCL可以始终如一地在各种公共数据集上实现与GCL相当复杂的各种公共数据集的最新性能。
translated by 谷歌翻译
自我监督的学习提供了一个有希望的途径,消除了在图形上的代表学习中的昂贵标签信息的需求。然而,为了实现最先进的性能,方法通常需要大量的负例,并依赖于复杂的增强。这可能是昂贵的,特别是对于大图。为了解决这些挑战,我们介绍了引导的图形潜伏(BGRL) - 通过预测输入的替代增强来学习图表表示学习方法。 BGRL仅使用简单的增强,并减轻了对否定例子对比的需求,因此通过设计可扩展。 BGRL胜过或匹配现有的几种建立的基准,同时降低了内存成本的2-10倍。此外,我们表明,BGR1可以缩放到半监督方案中的数亿个节点的极大的图表 - 实现最先进的性能并改善监督基线,其中表示仅通过标签信息而塑造。特别是,我们的解决方案以BGRL为中心,将kdd杯2021的开放图基准的大规模挑战组成了一个获奖条目,在比所有先前可用的基准更大的级别的图形订单上,从而展示了我们方法的可扩展性和有效性。
translated by 谷歌翻译
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data. However, its reliance on data augmentation and its quadratic computational complexity might lead to inconsistency and inefficiency problems. To mitigate these limitations, in this paper, we introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL in short). Local-GCL consists of two key designs: 1) We fabricate the positive examples for each node directly using its first-order neighbors, which frees our method from the reliance on carefully-designed graph augmentations; 2) To improve the efficiency of contrastive learning on graphs, we devise a kernelized contrastive loss, which could be approximately computed in linear time and space complexity with respect to the graph size. We provide theoretical analysis to justify the effectiveness and rationality of the proposed methods. Experiments on various datasets with different scales and properties demonstrate that in spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
translated by 谷歌翻译
Inspired by the success of contrastive learning (CL) in computer vision and natural language processing, graph contrastive learning (GCL) has been developed to learn discriminative node representations on graph datasets. However, the development of GCL on Heterogeneous Information Networks (HINs) is still in the infant stage. For example, it is unclear how to augment the HINs without substantially altering the underlying semantics, and how to design the contrastive objective to fully capture the rich semantics. Moreover, early investigations demonstrate that CL suffers from sampling bias, whereas conventional debiasing techniques are empirically shown to be inadequate for GCL. How to mitigate the sampling bias for heterogeneous GCL is another important problem. To address the aforementioned challenges, we propose a novel Heterogeneous Graph Contrastive Multi-view Learning (HGCML) model. In particular, we use metapaths as the augmentation to generate multiple subgraphs as multi-views, and propose a contrastive objective to maximize the mutual information between any pairs of metapath-induced views. To alleviate the sampling bias, we further propose a positive sampling strategy to explicitly select positives for each node via jointly considering semantic and structural information preserved on each metapath view. Extensive experiments demonstrate HGCML consistently outperforms state-of-the-art baselines on five real-world benchmark datasets.
translated by 谷歌翻译
尽管有关超图的机器学习吸引了很大的关注,但大多数作品都集中在(半)监督的学习上,这可能会导致繁重的标签成本和不良的概括。最近,对比学习已成为一种成功的无监督表示学习方法。尽管其他领域中对比度学习的发展繁荣,但对超图的对比学习仍然很少探索。在本文中,我们提出了Tricon(三个方向对比度学习),这是对超图的对比度学习的一般框架。它的主要思想是三个方向对比度,具体来说,它旨在在两个增强视图中最大化同一节点之间的协议(a),(b)在同一节点之间以及(c)之间,每个组之间的成员及其成员之间的协议(b) 。加上简单但令人惊讶的有效数据增强和负抽样方案,这三种形式的对比使Tricon能够在节点嵌入中捕获显微镜和介观结构信息。我们使用13种基线方法,5个数据集和两个任务进行了广泛的实验,这证明了Tricon的有效性,最明显的是,Tricon始终优于无监督的竞争对手,而且(半)受监督的竞争对手,大多数是由大量的节点分类的大量差额。
translated by 谷歌翻译
在异质图上的自我监督学习(尤其是对比度学习)方法可以有效地摆脱对监督数据的依赖。同时,大多数现有的表示学习方法将异质图嵌入到欧几里得或双曲线的单个几何空间中。这种单个几何视图通常不足以观察由于其丰富的语义和复杂结构而观察到异质图的完整图片。在这些观察结果下,本文提出了一种新型的自我监督学习方法,称为几何对比度学习(GCL),以更好地表示监督数据是不可用时的异质图。 GCL同时观察了从欧几里得和双曲线观点的异质图,旨在强烈合并建模丰富的语义和复杂结构的能力,这有望为下游任务带来更多好处。 GCL通过在局部局部和局部全球语义水平上对比表示两种几何视图之间的相互信息。在四个基准数据集上进行的广泛实验表明,在三个任务上,所提出的方法在包括节点分类,节点群集和相似性搜索在内的三个任务上都超过了强基础,包括无监督的方法和监督方法。
translated by 谷歌翻译
Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the agreement of representations in the two views. Despite the prosperous development of graph CL methods, the design of graph augmentation schemes-a crucial component in CL-remains rarely explored. We argue that the data augmentation schemes should preserve intrinsic structures and attributes of graphs, which will force the model to learn representations that are insensitive to perturbation on unimportant nodes and edges. However, most existing methods adopt uniform data augmentation schemes, like uniformly dropping edges and uniformly shuffling features, leading to suboptimal performance. In this paper, we propose a novel graph contrastive representation learning method with adaptive augmentation that incorporates various priors for topological and semantic aspects of the graph. Specifically, on the topology level, we design augmentation schemes based on node centrality measures to highlight important connective structures. On the node attribute level, we corrupt node features by adding more noise to unimportant node features, to enforce the model to recognize underlying semantic information. We perform extensive experiments of node classification on a variety of real-world datasets. Experimental results demonstrate that our proposed method consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts, which validates the effectiveness of the proposed contrastive framework with adaptive augmentation. CCS CONCEPTS• Computing methodologies → Unsupervised learning; Neural networks; Learning latent representations.
translated by 谷歌翻译
Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive learning process in GCL is performed on top of the representations learned by a graph neural network (GNN) backbone, which transforms and propagates the node contextual information based on its local neighborhoods. However, nodes sharing similar characteristics may not always be geographically close, which poses a great challenge for unsupervised GCL efforts due to their inherent limitations in capturing such global graph knowledge. In this work, we address their inherent limitations by proposing a simple yet effective framework -- Simple Neural Networks with Structural and Semantic Contrastive Learning} (S^3-CL). Notably, by virtue of the proposed structural and semantic contrastive learning algorithms, even a simple neural network can learn expressive node representations that preserve valuable global structural and semantic patterns. Our experiments demonstrate that the node representations learned by S^3-CL achieve superior performance on different downstream tasks compared with the state-of-the-art unsupervised GCL methods. Implementation and more experimental details are publicly available at \url{https://github.com/kaize0409/S-3-CL.}
translated by 谷歌翻译
图级表示在各种现实世界中至关重要,例如预测分子的特性。但是实际上,精确的图表注释通常非常昂贵且耗时。为了解决这个问题,图形对比学习构造实例歧视任务,将正面对(同一图的增强对)汇总在一起,并将负面对(不同图的增强对)推开,以进行无监督的表示。但是,由于为了查询,其负面因素是从所有图中均匀抽样的,因此现有方法遭受关键采样偏置问题的损失,即,否定物可能与查询具有相同的语义结构,从而导致性能降解。为了减轻这种采样偏见问题,在本文中,我们提出了一种典型的图形对比度学习(PGCL)方法。具体而言,PGCL通过将语义相似的图形群群归为同一组的群集数据的基础语义结构,并同时鼓励聚类的一致性,以实现同一图的不同增强。然后给出查询,它通过从与查询群集不同的群集中绘制图形进行负采样,从而确保查询及其阴性样本之间的语义差异。此外,对于查询,PGCL根据其原型(集群质心)和查询原型之间的距离进一步重新重新重新重新重新享受其负样本,从而使那些具有中等原型距离的负面因素具有相对较大的重量。事实证明,这种重新加权策略比统一抽样更有效。各种图基准的实验结果证明了我们的PGCL比最新方法的优势。代码可在https://github.com/ha-lins/pgcl上公开获取。
translated by 谷歌翻译
关于图表的深度学习最近吸引了重要的兴趣。然而,大多数作品都侧重于(半)监督学习,导致缺点包括重标签依赖,普遍性差和弱势稳健性。为了解决这些问题,通过良好设计的借口任务在不依赖于手动标签的情况下提取信息知识的自我监督学习(SSL)已成为图形数据的有希望和趋势的学习范例。与计算机视觉和自然语言处理等其他域的SSL不同,图表上的SSL具有独家背景,设计理念和分类。在图表的伞下自我监督学习,我们对采用图表数据采用SSL技术的现有方法及时及全面的审查。我们构建一个统一的框架,数学上正式地规范图表SSL的范例。根据借口任务的目标,我们将这些方法分为四类:基于生成的,基于辅助性的,基于对比的和混合方法。我们进一步描述了曲线图SSL在各种研究领域的应用,并总结了绘图SSL的常用数据集,评估基准,性能比较和开源代码。最后,我们讨论了该研究领域的剩余挑战和潜在的未来方向。
translated by 谷歌翻译
随着对比学习的兴起,无人监督的图形表示学习最近一直蓬勃发展,甚至超过了一些机器学习任务中的监督对应物。图表表示的大多数对比模型学习侧重于最大化本地和全局嵌入之间的互信息,或主要取决于节点级别的对比嵌入。然而,它们仍然不足以全面探索网络拓扑的本地和全球视图。虽然前者认为本地全球关系,但其粗略的全球信息导致本地和全球观点之间的思考。后者注重节点级别对齐,以便全局视图的作用出现不起眼。为避免落入这两个极端情况,我们通过对比群集分配来提出一种新颖的无监督图形表示模型,称为GCCA。通过组合聚类算法和对比学习,它有动力综合利用本地和全球信息。这不仅促进了对比效果,而且还提供了更高质量的图形信息。同时,GCCA进一步挖掘群集级信息,这使得它能够了解除了图形拓扑之外的节点之间的难以捉摸的关联。具体地,我们首先使用不同的图形增强策略生成两个增强的图形,然后使用聚类算法分别获取其群集分配和原型。所提出的GCCA进一步强制不同增强图中的相同节点来通过最小化交叉熵损失来互相识别它们的群集分配。为了展示其有效性,我们将在三个不同的下游任务中与最先进的模型进行比较。实验结果表明,GCCA在大多数任务中具有强大的竞争力。
translated by 谷歌翻译
图表分类具有生物信息学,社会科学,自动假新闻检测,Web文档分类等中的应用程序。在许多实践方案中,包括网络级应用程序,其中标签稀缺或难以获得,无人监督的学习是一种自然范式,但它交易表现。最近,对比学习(CL)使得无监督的计算机视觉模型能够竞争对抗监督。分析Visual CL框架的理论和实证工作发现,利用大型数据集和域名感知增强对于框架成功至关重要。有趣的是,图表CL框架通常会在使用较小数据的顺序的同时报告高性能,并且使用可能损坏图形的底层属性的域名增强(例如,节点或边缘丢弃,功能捕获)。通过这些差异的激励,我们寻求确定:(i)为什么现有的图形Cl框架尽管增加了增强和有限的数据; (ii)是否遵守Visual CL原理可以提高图形分类任务的性能。通过广泛的分析,我们识别图形数据增强和评估协议的缺陷实践,这些协议通常用于图形CL文献中,并提出了未来的研究和应用的改进的实践和理智检查。我们表明,在小型基准数据集上,图形神经网络的归纳偏差可以显着补偿现有框架的局限性。在采用相对较大的图形分类任务的研究中,我们发现常用的域名忽视增强的表现不佳,同时遵守Visual Cl中的原则可以显着提高性能。例如,在基于图形的文档分类中,可以用于更好的Web搜索,我们显示任务相关的增强提高了20%的准确性。
translated by 谷歌翻译
Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner. Existing methods construct the contrastive samples by adding perturbations to the graph structure or node attributes. Although impressive results are achieved, it is rather blind to the wealth of prior information assumed: with the increase of the perturbation degree applied on the original graph, 1) the similarity between the original graph and the generated augmented graph gradually decreases; 2) the discrimination between all nodes within each augmented view gradually increases. In this paper, we argue that both such prior information can be incorporated (differently) into the contrastive learning paradigm following our general ranking framework. In particular, we first interpret CL as a special case of learning to rank (L2R), which inspires us to leverage the ranking order among positive augmented views. Meanwhile, we introduce a self-ranking paradigm to ensure that the discriminative information among different nodes can be maintained and also be less altered to the perturbations of different degrees. Experiment results on various benchmark datasets verify the effectiveness of our algorithm compared with the supervised and unsupervised models.
translated by 谷歌翻译
Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL into graph modeling, dubbed as graph contrastive learning (GCL). However, generating contrastive views in graphs is more challenging than that in images, since we have little prior knowledge on how to significantly augment a graph without changing its labels. We argue that typical data augmentation techniques (e.g., edge dropping) in GCL cannot generate diverse enough contrastive views to filter out noises. Moreover, previous GCL methods employ two view encoders with exactly the same neural architecture and tied parameters, which further harms the diversity of augmented views. To address this limitation, we propose a novel paradigm named model augmented GCL (MA-GCL), which will focus on manipulating the architectures of view encoders instead of perturbing graph inputs. Specifically, we present three easy-to-implement model augmentation tricks for GCL, namely asymmetric, random and shuffling, which can respectively help alleviate high- frequency noises, enrich training instances and bring safer augmentations. All three tricks are compatible with typical data augmentations. Experimental results show that MA-GCL can achieve state-of-the-art performance on node classification benchmarks by applying the three tricks on a simple base model. Extensive studies also validate our motivation and the effectiveness of each trick. (Code, data and appendix are available at https://github.com/GXM1141/MA-GCL. )
translated by 谷歌翻译
对比度学习(CL)已成为无监督表示学习的主要技术,该技术将锚固的增强版本相互接近(正样本),并将其他样品(负)(负)的嵌入到分开。正如最近的研究所揭示的那样,CL可以受益于艰苦的负面因素(与锚定的负面因素)。但是,当我们在图对比度学习中采用现有的其他域的硬采矿技术(GCL)时,我们会观察到有限的好处。我们对该现象进行实验和理论分析,发现它可以归因于图神经网络(GNNS)的信息传递。与其他域中的CL不同,大多数硬否负面因素是潜在的假否(与锚共享同一类的负面因素),如果仅根据锚和本身之间的相似性选择它们,这将不必要地推开同一类的样本。为了解决这种缺陷,我们提出了一种称为\ textbf {progcl}的有效方法,以估计否定的概率是真实的,这构成了更合适的衡量否定性与否定性的衡量标准。此外,我们设计了两个方案(即\ textbf {progcl-weight}和\ textbf {progcl-mix}),以提高GCL的性能。广泛的实验表明,POGCL对基本GCL方法具有显着和一致的改进,并在几个无监督的基准上产生多个最新的结果,甚至超过了受监督的基准。此外,Progcl很容易将基于负面的GCL方法插入以改进性能的GCL方法。我们以\ textColor {magenta} {\ url {https://github.com/junxia97/progcl}}}发布代码。
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
图对比度学习(GCL)改善了图表的学习,从而导致SOTA在各种下游任务上。图扩大步骤是GCL的重要但几乎没有研究的步骤。在本文中,我们表明,通过图表增强获得的节点嵌入是高度偏差的,在某种程度上限制了从学习下游任务的学习区分特征的对比模型。隐藏功能(功能增强)。受到所谓矩阵草图的启发,我们提出了Costa,这是GCL的一种新颖的协变功能空间增强框架,该框架通过维护原始功能的``好草图''来生成增强功能。为了强调Costa的特征增强功能的优势,我们研究了一个保存记忆和计算的单视图设置(除了多视图ONE)。我们表明,与基于图的模型相比,带有Costa的功能增强功能可比较/更好。
translated by 谷歌翻译
Heterogeneous graph contrastive learning has received wide attention recently. Some existing methods use meta-paths, which are sequences of object types that capture semantic relationships between objects, to construct contrastive views. However, most of them ignore the rich meta-path context information that describes how two objects are connected by meta-paths. On the other hand, they fail to distinguish hard negatives from false negatives, which could adversely affect the model performance. To address the problems, we propose MEOW, a heterogeneous graph contrastive learning model that considers both meta-path contexts and weighted negative samples. Specifically, MEOW constructs a coarse view and a fine-grained view for contrast. The former reflects which objects are connected by meta-paths, while the latter uses meta-path contexts and characterizes the details on how the objects are connected. We take node embeddings in the coarse view as anchors, and construct positive and negative samples from the fine-grained view. Further, to distinguish hard negatives from false negatives, we learn weights of negative samples based on node clustering. We also use prototypical contrastive learning to pull close embeddings of nodes in the same cluster. Finally, we conduct extensive experiments to show the superiority of MEOW against other state-of-the-art methods.
translated by 谷歌翻译