图形神经网络(GNNS)正在快速成为在多个域中学习图形结构化数据的标准方法,但它们在其决策中缺乏透明度。已经开发了几种基于扰动的方法,以提供对GNN的决策过程的见解。由于这是一个早期研究区域,用于评估生成的解释的方法和数据缺乏成熟。我们探索了这些现有的方法,并识别三个主要领域的普通缺陷:(1)合成数据生成过程,(2)评估指标,以及(3)最终呈现解释。为此目的,我们执行一个实证研究,以探索这些陷阱以及他们意外的后果,并提出补救措施来减轻它们的效果。
translated by 谷歌翻译
Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs. GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models and explaining predictions made by GNNs remains unsolved. Here we propose GNNEXPLAINER, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task. Given an instance, GNNEXPLAINER identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction. Further, GNNEXPLAINER can generate consistent and concise explanations for an entire class of instances. We formulate GNNEXPLAINER as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures. Experiments on synthetic and real-world graphs show that our approach can identify important graph structures as well as node features, and outperforms alternative baseline approaches by up to 43.0% in explanation accuracy. GNNEXPLAINER provides a variety of benefits, from the ability to visualize semantically relevant structures to interpretability, to giving insights into errors of faulty GNNs.
translated by 谷歌翻译
深度学习方法正在实现许多人工智能任务上的不断增长。深层模型的一个主要局限性是它们不适合可解释性。可以通过开发事后技术来解释预测,从而产生解释性领域,从而规避这种限制。最近,关于图像和文本的深层模型的解释性取得了重大进展。在图数据的领域,图形神经网络(GNN)及其解释性正在迅速发展。但是,既没有对GNN解释性方法的统一处理,也没有标准的基准和测试床。在这项调查中,我们提供了当前GNN解释性方法的统一和分类观点。我们对这一主题的统一和分类治疗对现有方法的共同性和差异阐明了灯光,并为进一步的方法论发展奠定了基础。为了促进评估,我们生成了一组专门用于GNN解释性的基准图数据集。我们总结了当前的数据集和指标,以评估GNN的解释性。总的来说,这项工作提供了GNN解释性和评估标准化测试床的统一方法论。
translated by 谷歌翻译
解释机器学习决策的问题是经过深入研究和重要的。我们对一种涉及称为图形神经网络的图形数据的特定类型的机器学习模型感兴趣。众所周知,由于缺乏公认的基准,评估图形神经网络(GNN)的可解释性方法是具有挑战性的。鉴于GNN模型,存在几种可解释性方法来解释具有多种(有时相互矛盾的)方法论的GNN模型。在本文中,我们提出了一个基准,用于评估称为Bagel的GNN的解释性方法。在百吉饼中,我们首先提出了四种不同的GNN解释评估制度 - 1)忠诚,2)稀疏性,3)正确性。 4)合理性。我们在现有文献中调和多个评估指标,并涵盖了各种概念以进行整体评估。我们的图数据集范围从引文网络,文档图,到分子和蛋白质的图。我们对四个GNN模型和九个有关节点和图形分类任务的事后解释方法进行了广泛的实证研究。我们打开基准和参考实现,并在https://github.com/mandeep-rathee/bagel-benchmark上提供它们。
translated by 谷歌翻译
在高措施应用中大量部署图神经网络(GNNS)对对噪声的强大解释产生了强烈的需求,这些解释与人类的直觉很好。大多数现有方法通过识别与预测有很强相关性的输入图的子图来生成解释。这些解释对噪声并不强大,因为独立优化单个输入的相关性很容易过分拟合噪声。此外,它们与人类直觉并不十分吻合,因为从输入图中删除已识别的子图并不一定会改变预测结果。在本文中,我们提出了一种新颖的方法,可以通过在类似的输入图上明确建模GNNS的共同决策逻辑来生成对GNN的强大反事实解释。我们的解释自然对噪声是强大的,因为它们是由控制许多类似输入图的GNN的共同决策边界产生的。该解释也与人类的直觉很好地吻合,因为从输入图中的解释中删除了一组边缘,从而显着改变了预测。许多公共数据集上的详尽实验证明了我们方法的出色性能。
translated by 谷歌翻译
In this paper, we investigate the degree of explainability of graph neural networks (GNNs). Existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here, we propose a meta-learning framework for improving the level of explainability of a GNN directly at training time, by steering the optimization procedure towards what we call `interpretable minima'. Our framework (called MATE, MetA-Train to Explain) jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms that explain the model's decisions in a human-friendly way. In particular, we meta-train the model's parameters to quickly minimize the error of an instance-level GNNExplainer trained on-the-fly on randomly sampled nodes. The final internal representation relies upon a set of features that can be `better' understood by an explanation algorithm, e.g., another instance of GNNExplainer. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process. Experiments on synthetic and real-world datasets for node and graph classification show that we can produce models that are consistently easier to explain by different algorithms. Furthermore, this increase in explainability comes at no cost for the accuracy of the model.
translated by 谷歌翻译
与其他连接主义模型类似,图形神经网络(GNNS)缺乏决策透明度。已经开发了许多子象征方法来提供对GNN决策过程的见解。这些是解释性途中的第一个重要步骤,但是对于不是AI专家的用户来说,生成的解释通常很难理解。为了克服这个问题,我们介绍了一种概念方法,组合了亚象征性和象征方法以实现人以人为中心的解释,其包含域知识和因果关系。我们还将保真度的概念介绍为评估解释如何对GNN的内部决策过程的指标。使用化学数据集和本体的评估显示了我们方法的解释性值和可靠性。
translated by 谷歌翻译
Explainability of Graph Neural Networks (GNNs) is critical to various GNN applications but remains an open challenge. A convincing explanation should be both necessary and sufficient simultaneously. However, existing GNN explaining approaches focus on only one of the two aspects, necessity or sufficiency, or a trade-off between the two. To search for the most necessary and sufficient explanation, the Probability of Necessity and Sufficiency (PNS) can be applied since it can mathematically quantify the necessity and sufficiency of an explanation. Nevertheless, the difficulty of obtaining PNS due to non-monotonicity and the challenge of counterfactual estimation limits its wide use. To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound. Specifically, we employ nearest neighbor matching to generate counterfactual samples for the features, which is different from the random perturbation. In particular, NSEG combines the edges and node features to generate an explanation, where the common edge explanation is a special case of the combined explanation. Empirical study shows that NSEG achieves excellent performance in generating the most necessary and sufficient explanations among a series of state-of-the-art methods.
translated by 谷歌翻译
With the rapid deployment of graph neural networks (GNNs) based techniques into a wide range of applications such as link prediction, node classification, and graph classification the explainability of GNNs has become an indispensable component for predictive and trustworthy decision-making. Thus, it is critical to explain why graph neural network (GNN) makes particular predictions for them to be believed in many applications. Some GNNs explainers have been proposed recently. However, they lack to generate accurate and real explanations. To mitigate these limitations, we propose GANExplainer, based on Generative Adversarial Network (GAN) architecture. GANExplainer is composed of a generator to create explanations and a discriminator to assist with the Generator development. We investigate the explanation accuracy of our models by comparing the performance of GANExplainer with other state-of-the-art methods. Our empirical results on synthetic datasets indicate that GANExplainer improves explanation accuracy by up to 35\% compared to its alternatives.
translated by 谷歌翻译
由于事后解释越来越多地用于了解图神经网络(GNN)的行为,因此评估GNN解释的质量和可靠性至关重要。但是,评估GNN解释的质量是具有挑战性的,因为现有的图形数据集对给定任务没有或不可靠的基础真相解释。在这里,我们介绍了一个合成图数据生成器ShapeGgen,该生成可以生成各种基准数据集(例如,不同的图形大小,度分布,同粒细胞与异性图)以及伴随着地面真相解释。此外,生成各种合成数据集和相应的基础真相解释的灵活性使我们能够模仿各种现实世界应用程序生成的数据。我们将ShapeGgen和几个现实图形数据集包括在开源图形图库GraphXai中。除了带有基础真相说明的合成和现实图形数据集外,GraphXAI还提供数据加载程序,数据处理功能,可视化器,GNN模型实现和评估指标,以基准基准GNN解释性方法的性能。
translated by 谷歌翻译
作为当今最受欢迎的机器学习模型之一,Graph神经网络(GNN)最近引起了激烈的兴趣,其解释性也引起了人们的兴趣。用户对更好地了解GNN模型及其结果越来越感兴趣。不幸的是,当今的GNN评估框架通常依赖于合成数据集,从而得出有限范围的结论,因为问题实例缺乏复杂性。由于GNN模型被部署到更关键的任务应用程序中,因此我们迫切需要使用GNN解释性方法的共同评估协议。在本文中,据我们最大的知识,我们提出了针对GNN解释性的第一个系统评估框架,考虑了三种不同的“用户需求”的解释性:解释焦点,掩盖性质和掩蔽转换。我们提出了一个独特的指标,该指标将忠诚度措施结合在一起,并根据其足够或必要的质量对解释进行分类。我们将自己范围用于节点分类任务,并比较GNN的输入级解释性领域中最具代表性的技术。对于广泛使用的合成基准测试,令人惊讶的是,诸如个性化Pagerank之类的浅水技术在最小计算时间内具有最佳性能。但是,当图形结构更加复杂并且节点具有有意义的特征时,根据我们的评估标准,基于梯度的方法,尤其是显着性。但是,没有人在所有评估维度上占主导地位,而且总会有一个权衡。我们在eBay图上的案例研究中进一步应用了我们的评估协议,以反映生产环境。
translated by 谷歌翻译
图神经网络(GNN)是一类流行的机器学习模型。受到学习解释(L2X)范式的启发,我们提出了L2XGNN,这是一个可解释的GNN的框架,该框架通过设计提供了忠实的解释。L2XGNN学习了一种选择解释性子图(主题)的机制,该机制仅在GNNS消息通话操作中使用。L2XGNN能够为每个输入图选择具有特定属性的子图,例如稀疏和连接。对主题施加这种限制通常会导致更容易解释和有效的解释。几个数据集的实验表明,L2XGNN使用整个输入图实现了与基线方法相同的分类精度,同时确保仅使用提供的解释来进行预测。此外,我们表明L2XGNN能够识别负责预测图形属性的主题。
translated by 谷歌翻译
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions. Though various algorithms are proposed, most of them formalize this task by searching the minimal subgraph which can preserve original predictions. However, an inductive bias is deep-rooted in this framework: several subgraphs can result in the same or similar outputs as the original graphs. Consequently, they have the danger of providing spurious explanations and fail to provide consistent explanations. Applying them to explain weakly-performed GNNs would further amplify these issues. To address this problem, we theoretically examine the predictions of GNNs from the causality perspective. Two typical reasons of spurious explanations are identified: confounding effect of latent variables like distribution shift, and causal factors distinct from the original input. Observing that both confounding effects and diverse causal rationales are encoded in internal representations, we propose a simple yet effective countermeasure by aligning embeddings. Concretely, concerning potential shifts in the high-dimensional space, we design a distribution-aware alignment algorithm based on anchors. This new objective is easy to compute and can be incorporated into existing techniques with no or little effort. Theoretical analysis shows that it is in effect optimizing a more faithful explanation objective in design, which further justifies the proposed approach.
translated by 谷歌翻译
由于图形神经网络(GNN)在各个域中的出色性能,因此对GNN解释问题越来越感兴趣“ \ emph {输入图的哪一部分是决定模型决定的最关键?}“现有的解释?方法集中在监督的设置,例如节点分类和图形分类上,而无监督的图形表示学习的解释仍未探索。当部署高级决策情况时,图表表示的不透明可能会导致意外风险。在本文中,我们推进了信息瓶颈原理(IB),以解决无监督的图表表示所提出的解释问题,这导致了一个新颖的原理,\ textit {无监督的子图表信息瓶颈}(USIB)。我们还理论上分析了标签空间上图表和解释子图之间的联系,这表明表示的表现力和鲁棒性有益于解释性子图的保真度。合成和现实世界数据集的实验结果证明了我们发达的解释器的优越性以及我们的理论分析的有效性。
translated by 谷歌翻译
最近,引入了亚图增强图神经网络(SGNN),以增强图形神经网络(GNN)的表达能力,事实证明,该功能不高于一维Weisfeiler-Leman同构测试。新的范式建议使用从输入图中提取的子图提高模型的表现力,但是额外的复杂性加剧了GNNS中本来可以具有挑战性的问题:解释其预测。在这项工作中,我们将PGEXPlainer(GNNS的最新解释者之一)改编为SGNN。拟议的解释器解释了所有不同子图的贡献,并可以产生人类可以解释的有意义的解释。我们在真实和合成数据集上执行的实验表明,我们的框架成功地解释了SGNN在图形分类任务上的决策过程。
translated by 谷歌翻译
我们研究了图神经网络(GNN)的解释性,作为阐明其工作机制的一步。尽管大多数当前方法都集中在解释图节点,边缘或功能上,但我们认为,作为GNNS的固有功能机制,消息流对执行解释性更为自然。为此,我们在这里提出了一种新颖的方法,即FlowX,以通过识别重要的消息流来解释GNN。为了量化流量的重要性,我们建议遵循合作游戏理论中沙普利价值观的哲学。为了解决计算所有联盟边际贡献的复杂性,我们提出了一个近似方案,以计算类似沙普利的值,作为进一步再分配训练的初步评估。然后,我们提出一种学习算法来训练流量评分并提高解释性。关于合成和现实世界数据集的实验研究表明,我们提出的FlowX导致GNN的解释性提高。
translated by 谷歌翻译
隐私性和解释性是实现值得信赖的机器学习的两种重要成分。我们通过图形重建攻击研究了图机学习中这两个方面的相互作用。这里的对手的目的是重建给定模型解释的训练数据的图形结构。根据对手可用的不同种类的辅助信息,我们提出了几种图形重建攻击。我们表明,事后功能解释的其他知识大大提高了这些攻击的成功率。此外,我们详细研究了攻击性能相对于三种不同类别的图形神经网络的解释方法的差异:基于梯度,基于扰动和基于替代模型的方法。虽然基于梯度的解释在图形结构方面显示最多,但我们发现这些解释并不总是在实用程序上得分很高。对于其他两类的解释,隐私泄漏随着解释实用程序的增加而增加。最后,我们提出了基于随机响应机制的防御,以释放大大降低攻击成功率的解释。我们的匿名代码可用。
translated by 谷歌翻译
图形神经网络(GNN)已成为编码图形结构数据的强大工具。由于其广泛的应用程序,越来越需要开发工具来解释GNN如何做出给定的图形结构数据决定。现有的基于学习的GNN解释方法在培训中是特定于任务的,因此遭受了关键的缺点。具体而言,它们无法为使用单个解释器提供多任务预测模型的解释。在GNN以自我监督的方式训练的情况下,他们也无法提供解释,并且在未来的下游任务中使用了结果表示。为了解决这些局限性,我们提出了一个任务不合时宜的GNN解释器(TAGE),该解释器(Tage)独立于下游模型,并在自学人员的情况下接受了训练,而对下游任务不了解。 Tage可以通过看不见的下游任务来解释GNN嵌入模型,并可以有效解释多任务模型。我们的广泛实验表明,通过使用相同的模型来解释多个下游任务的预测,同时实现了与当前最新的GNN解释方法一样好甚至更好的解释质量,可以显着提高解释效率。我们的代码可公开作为DIG库的一部分,网址为https://github.com/divelab/dig/tree/main/main/dig/xgraph/tage/。
translated by 谷歌翻译
图形神经网络的不透明推理导致缺乏人类的信任。现有的图形网络解释器试图通过提供事后解释来解决此问题,但是,它们无法使模型本身更容易解释。为了填补这一空白,我们介绍了概念编码器模块,这是图形网络的第一个可区分概念 - 发现方法。所提出的方法使图形网络可以通过首先发现图形概念,然后使用这些来解决任务来解释。我们的结果表明,这种方法允许图形网络:(i)达到模型准确性与它们的等效香草版本相当,(ii)发现有意义的概念,以实现高概念完整性和纯度得分,(iii)提供基于高质量的概念逻辑。对其预测的解释,以及(iv)在测试时支持有效的干预措施:这些可以提高人类的信任并显着提高模型绩效。
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