图表神经网络(GNNS)在半监督学习场景中取得了显着的成功。图形神经网络中的消息传递机制有助于未标记的节点收集标记邻居的监督信号。在这项工作中,我们调查了一项广泛采用的半监督学习方法之一的一致性正则化的一致性,可以帮助提高图形神经网络的性能。我们重新审视图形神经网络的两种一致性正则化方法。一个是简单的一致性正则化(SCR),另一个是均值是均值 - 教师一致性正则化(MCR)。我们将一致性正则化方法与两个最先进的GNN结合起来并在OGBN-Products数据集上进行实验。通过一致性正常化,可以在具有和无外数据的OGBN-Products数据集中提高最先进的GNN的性能0.3%。
translated by 谷歌翻译
众所周知,图形神经网络(GNN)的成功高度依赖于丰富的人类通知数据,这在实践中努力获得,并且并非总是可用的。当只有少数标记的节点可用时,如何开发高效的GNN仍在研究。尽管已证明自我训练对于半监督学习具有强大的功能,但其在图形结构数据上的应用可能会失败,因为(1)不利用较大的接收场来捕获远程节点相互作用,这加剧了传播功能的难度 - 标记节点到未标记节点的标签模式; (2)有限的标记数据使得在不同节点类别中学习良好的分离决策边界而不明确捕获基本的语义结构,这是一项挑战。为了解决捕获信息丰富的结构和语义知识的挑战,我们提出了一个新的图数据增强框架,AGST(增强图自训练),该框架由两个新的(即结构和语义)增强模块构建。 GST骨干。在这项工作中,我们研究了这个新颖的框架是否可以学习具有极有限标记节点的有效图预测模型。在有限标记节点数据的不同情况下,我们对半监督节点分类进行全面评估。实验结果证明了新的数据增强框架对节点分类的独特贡献,几乎没有标记的数据。
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
图形神经网络是一种强大的深度学习工具,用于建模图形结构化数据,在众多图形学习任务上表现出了出色的性能。为了解决深图学习中的数据噪声和数据稀缺性问题,最近有关图形数据的研究已加剧。但是,常规数据增强方法几乎无法处理具有多模式性的非欧几里得空间中定义的图形结构化数据。在这项调查中,我们正式提出了图数据扩展的问题,并进一步审查了代表性技术及其在不同深度学习问题中的应用。具体而言,我们首先提出了图形数据扩展技术的分类法,然后通过根据增强信息方式对相关工作进行分类,从而提供结构化的审查。此外,我们总结了以数据为中心的深图学习中两个代表性问题中图数据扩展的应用:(1)可靠的图形学习,重点是增强输入图的实用性以及通过图数据增强的模型容量; (2)低资源图学习,其针对通过图数据扩大标记的训练数据量表的目标。对于每个问题,我们还提供层次结构问题分类法,并审查与图数据增强相关的现有文献。最后,我们指出了有希望的研究方向和未来研究的挑战。
translated by 谷歌翻译
Graph Neural Networks (GNNs) have been widely applied in the semi-supervised node classification task, where a key point lies in how to sufficiently leverage the limited but valuable label information. Most of the classical GNNs solely use the known labels for computing the classification loss at the output. In recent years, several methods have been designed to additionally utilize the labels at the input. One part of the methods augment the node features via concatenating or adding them with the one-hot encodings of labels, while other methods optimize the graph structure by assuming neighboring nodes tend to have the same label. To bring into full play the rich information of labels, in this paper, we present a label-enhanced learning framework for GNNs, which first models each label as a virtual center for intra-class nodes and then jointly learns the representations of both nodes and labels. Our approach could not only smooth the representations of nodes belonging to the same class, but also explicitly encode the label semantics into the learning process of GNNs. Moreover, a training node selection technique is provided to eliminate the potential label leakage issue and guarantee the model generalization ability. Finally, an adaptive self-training strategy is proposed to iteratively enlarge the training set with more reliable pseudo labels and distinguish the importance of each pseudo-labeled node during the model training process. Experimental results on both real-world and synthetic datasets demonstrate our approach can not only consistently outperform the state-of-the-arts, but also effectively smooth the representations of intra-class nodes.
translated by 谷歌翻译
灵感来自深度学习的广泛成功,已经提出了图表神经网络(GNNS)来学习表达节点表示,并在各种图形学习任务中表现出有希望的性能。然而,现有的努力主要集中在提供相对丰富的金色标记节点的传统半监督设置。虽然数据标签是难以忍受的事实令人生畏的事实并且需要强化领域知识,但特别是在考虑图形结构数据的异质性时,它通常是不切实际的。在几次半监督的环境下,大多数现有GNN的性能不可避免地受到过度装备和过天际问题的破坏,在很大程度上由于标记数据的短缺。在本文中,我们提出了一种配备有新型元学习算法的解耦的网络架构来解决这个问题。从本质上讲,我们的框架META-PN通过META学习的标签传播策略在未标记节点上乘坐高质量的伪标签,这有效增强了稀缺标记的数据,同时在培训期间启用大型接受领域。广泛的实验表明,与各种基准数据集上的现有技术相比,我们的方法提供了简单且实质性的性能。
translated by 谷歌翻译
这项工作的作者提出了最近半监督的学习方法和相关作品的概述。尽管神经网络在各种应用中取得了显着的成功,但很少有强大的约束,包括需要大量标记数据。因此,半监督的学习是一种学习方案,其中稀缺标签和大量未标记的数据被用于训练模型(例如,深度神经网络)变得越来越重要。基于半监督学习的关键假设,这是多种假设,集群假设和连续性假设,工作回顾了最近的半监督学习方法。特别是,主要讨论了在半监督学习环境中使用深神网络的方法。此外,现有的作品首先是根据基本思想进行了分类并解释的,然后详细介绍了统一上述思想的整体方法。
translated by 谷歌翻译
Graph神经网络(GNN)最近在许多基于图的应用程序中都实现了最先进的性能。尽管具有很高的表现力,但他们通常需要在多个培训时期进行昂贵的递归邻里扩展,并面临可伸缩性问题。此外,它们中的大多数是不灵活的,因为它们仅限于固定跳跃社区,并且对不同节点的实际接受场需求不敏感。我们通过引入可扩展且灵活的图表多层感知器(GAMLP)来规避这些限制。随着非线性转化和特征传播的分离,GAMLP通过以预先计算的方式执行传播程序来显着提高可伸缩性和效率。有了三个原则的接受场注意力,GAMLP中的每个节点都具有灵活性和适应性,以利用接收场的不同尺寸的传播特征。我们对三个大型开放图基准(例如OGBN-PAPERS100M,OGBN产品和OGBN-MAG)进行了广泛的评估,这表明GAMLP不仅可以实现前面的性能,而且还提供了较高的可扩展性和效率。
translated by 谷歌翻译
This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of molecules and community analysis in social networks. Traditional graph kernel based methods are simple, yet effective for obtaining fixed-length representations for graphs but they suffer from poor generalization due to hand-crafted designs. There are also some recent methods based on language models (e.g. graph2vec) but they tend to only consider certain substructures (e.g. subtrees) as graph representatives. Inspired by recent progress of unsupervised representation learning, in this paper we proposed a novel method called InfoGraph for learning graph-level representations. We maximize the mutual information between the graph-level representation and the representations of substructures of different scales (e.g., nodes, edges, triangles). By doing so, the graph-level representations encode aspects of the data that are shared across different scales of substructures. Furthermore, we further propose InfoGraph*, an extension of InfoGraph for semi-supervised scenarios. InfoGraph* maximizes the mutual information between unsupervised graph representations learned by InfoGraph and the representations learned by existing supervised methods. As a result, the supervised encoder learns from unlabeled data while preserving the latent semantic space favored by the current supervised task. Experimental results on the tasks of graph classification and molecular property prediction show that InfoGraph is superior to state-of-the-art baselines and InfoGraph* can achieve performance competitive with state-of-the-art semi-supervised models.
translated by 谷歌翻译
知识蒸馏最近成为一种流行的技术,以改善卷积神经网络的模型泛化能力。然而,它对图形神经网络的影响小于令人满意的,因为图形拓扑和节点属性可能以动态方式改变,并且在这种情况下,静态教师模型引导学生培训不足。在本文中,我们通过在在线蒸馏时期同时培训一组图形神经网络来解决这一挑战,其中组知识发挥作用作为动态虚拟教师,并且有效地捕获了图形神经网络的结构变化。为了提高蒸馏性能,在学生之间转移两种知识,以增强彼此:在图形拓扑和节点属性中反映信息的本地知识,以及反映课程预测的全局知识。随着香草知识蒸馏等,在利用有效的对抗性循环学习框架,将全球知识与KL分歧转移。广泛的实验验证了我们提出的在线对抗蒸馏方法的有效性。
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
数据增强可帮助神经网络通过放大培训集来更好地推广,但它仍然是如何有效增强图数据以增强GNN的性能的开放问题(图形神经网络)。虽然大多数现有图形常规程序专注于通过添加/删除边缘来操纵图形拓扑结构,但我们提供了一种增强节点功能以获得更好性能的方法。我们提出标志(图中的免费大规模对抗动力增强),它在训练期间迭代地增强了基于梯度的对冲扰动的节点特征。通过使模型不变地在输入数据中的小波动中,我们的方法有助于模型推广到分布外的样本,并在测试时间提高模型性能。标志是图形数据的通用方法,它普遍存在节点分类,链路预测和图形分类任务中。标志也是非常灵活和可扩展的,并且可以使用任意GNN骨架和大规模数据集进行可部署。我们通过广泛的实验和消融研究证明了我们方法的功效和稳定性。我们还提供了直观的观察,以更深入地了解我们的方法。
translated by 谷歌翻译
节点分类是基于图形的基本任务,旨在预测未标记的节点的类别,对于哪种图形神经网络(GNN)是最新方法。在当前的GNN中,培训节点(或培训样本)在整个培训过程中得到平等的治疗。但是,样品的质量根据图结构而变化很大。因此,GNN的性能可能会受到两种类型的低质量样本的损害:(1)位于连接相邻类的类边界附近的类间节点。这些节点的表示缺乏其相应类的典型特征。由于GNN是数据驱动的方法,因此对这些节点进行培训可能会降低准确性。 (2)标记的节点。在实际图中,节点通常被错误标记,这会大大降低GNN的鲁棒性。为了减轻低质量样品的有害效果,我们提出clnode(用于节点分类的课程学习),该cl虫根据其质量自动调整样品的权重。具体而言,我们首先设计了基于邻里的难度测量器来准确测量样品的质量。随后,基于这些测量值,我们采用培训调度程序来调整每个训练时期的样本权重。为了评估clnode的有效性,我们通过将其应用于四个代表性的骨干GNN来进行广泛的实验。六个现实世界网络上的实验结果表明,clnode是一个通用框架,可以与各种GNN结合使用,以提高其准确性和鲁棒性。
translated by 谷歌翻译
图形神经网络(GNNS)在建模图形结构数据方面表明了它们的能力。但是,实际图形通常包含结构噪声并具有有限的标记节点。当在这些图表中培训时,GNN的性能会显着下降,这阻碍了许多应用程序的GNN。因此,与有限标记的节点开发抗噪声GNN是重要的。但是,这是一个相当有限的工作。因此,我们研究了在具有有限标记节点的嘈杂图中开发鲁棒GNN的新问题。我们的分析表明,嘈杂的边缘和有限的标记节点都可能损害GNN的消息传递机制。为减轻这些问题,我们提出了一种新颖的框架,该框架采用嘈杂的边缘作为监督,以学习去噪和密集的图形,这可以减轻或消除嘈杂的边缘,并促进GNN的消息传递,以缓解有限标记节点的问题。生成的边缘还用于规则地将具有标记平滑度的未标记节点的预测规范化,以更好地列车GNN。实验结果对现实世界数据集展示了在具有有限标记节点的嘈杂图中提出框架的稳健性。
translated by 谷歌翻译
We present Self Meta Pseudo Labels, a novel semi-supervised learning method similar to Meta Pseudo Labels but without the teacher model. We introduce a novel way to use a single model for both generating pseudo labels and classification, allowing us to store only one model in memory instead of two. Our method attains similar performance to the Meta Pseudo Labels method while drastically reducing memory usage.
translated by 谷歌翻译
Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the in-distribution hypothesis, has made great progress and attracted ever-increasing attention from the research community. In this paper, we comprehensively survey OOD generalization on graphs and present a detailed review of recent advances in this area. First, we provide a formal problem definition of OOD generalization on graphs. Second, we categorize existing methods into three classes from conceptually different perspectives, i.e., data, model, and learning strategy, based on their positions in the graph machine learning pipeline, followed by detailed discussions for each category. We also review the theories related to OOD generalization on graphs and introduce the commonly used graph datasets for thorough evaluations. Finally, we share our insights on future research directions. This paper is the first systematic and comprehensive review of OOD generalization on graphs, to the best of our knowledge.
translated by 谷歌翻译
Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many incompletely-annotated data instances. Since only part of the most confident positive samples are available and evidence is not enough to categorize the rest samples, many of these unlabeled data may also be the positive samples. Research on this topic is particularly useful and essential to many real-world tasks which demand very expensive labelling cost. For example, the recognition tasks in disease diagnosis, recommendation system and satellite image recognition may only have few positive samples that can be annotated by the experts. These methods mainly omit the intrinsic hardness of some unlabeled data, which can result in sub-optimal performance as a consequence of fitting the easy noisy data and not sufficiently utilizing the hard data. In this paper, we focus on improving the commonly-used nnPU with a novel training pipeline. We highlight the intrinsic difference of hardness of samples in the dataset and the proper learning strategies for easy and hard data. By considering this fact, we propose first splitting the unlabeled dataset with an early-stop strategy. The samples that have inconsistent predictions between the temporary and base model are considered as hard samples. Then the model utilizes a noise-tolerant Jensen-Shannon divergence loss for easy data; and a dual-source consistency regularization for hard data which includes a cross-consistency between student and base model for low-level features and self-consistency for high-level features and predictions, respectively.
translated by 谷歌翻译
图表卷积网络在基于图形的半监督学习方面取得了很大进展。现有方法主要假设通过图形边缘连接的节点容易具有相似的属性和标签,因此由本地图形结构平滑的特征可以揭示类相似性。然而,在许多真实情景中的图形结构和标签之间经常存在不匹配,其中结构可以传播最终影响模型性能的误导性功能或标签。在本文中,我们提出了一种多任务的自蒸馏框架,将自我监督的学习和自蒸煮注入图形卷积网络中,以分别地解决结构侧和标签侧的不匹配问题。首先,我们基于预先文本任务制定自我监督管道,以捕获图表中的不同程度的相似性。鼓励特征提取过程通过联合优化预文本任务和目标任务来捕获更复杂的接近。因此,从结构侧提高了本地特征聚合。其次,自蒸馏使用模型本身的软标签作为额外的监督,这与标签平滑有类似的效果。从分类管道和自我监督管道的知识共同蒸馏,以改善来自标签侧的模型的泛化能力。实验结果表明,该方法在几种经典图卷积架构下获得了显着性能增益。
translated by 谷歌翻译
培训深层神经网络以识别图像识别通常需要大规模的人类注释数据。为了减少深神经溶液对标记数据的依赖,文献中已经提出了最先进的半监督方法。尽管如此,在面部表达识别领域(FER)领域,使用这种半监督方法非常罕见。在本文中,我们介绍了一项关于最近提出的在FER背景下的最先进的半监督学习方法的全面研究。我们对八种半监督学习方法进行了比较研究当使用各种标记的样品时。我们还将这些方法的性能与完全监督的培训进行了比较。我们的研究表明,当培训现有的半监督方法时,每类标记的样本只有250个标记的样品可以产生可比的性能,而在完整标记的数据集中训练的完全监督的方法。为了促进该领域的进一步研究,我们在:https://github.com/shuvenduroy/ssl_fer上公开提供代码
translated by 谷歌翻译
In recent years, semi-supervised graph learning with data augmentation (DA) is currently the most commonly used and best-performing method to enhance model robustness in sparse scenarios with few labeled samples. Differing from homogeneous graph, DA in heterogeneous graph has greater challenges: heterogeneity of information requires DA strategies to effectively handle heterogeneous relations, which considers the information contribution of different types of neighbors and edges to the target nodes. Furthermore, over-squashing of information is caused by the negative curvature that formed by the non-uniformity distribution and strong clustering in complex graph. To address these challenges, this paper presents a novel method named Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation (HG-MDA). For the problem of heterogeneity of information in DA, node and topology augmentation strategies are proposed for the characteristics of heterogeneous graph. And meta-relation-based attention is applied as one of the indexes for selecting augmented nodes and edges. For the problem of over-squashing of information, triangle based edge adding and removing are designed to alleviate the negative curvature and bring the gain of topology. Finally, the loss function consists of the cross-entropy loss for labeled data and the consistency regularization for unlabeled data. In order to effectively fuse the prediction results of various DA strategies, the sharpening is used. Existing experiments on public datasets, i.e., ACM, DBLP, OGB, and industry dataset MB show that HG-MDA outperforms current SOTA models. Additionly, HG-MDA is applied to user identification in internet finance scenarios, helping the business to add 30% key users, and increase loans and balances by 3.6%, 11.1%, and 9.8%.
translated by 谷歌翻译