As many deep anomaly detection models have been deployed in the real-world, interpretable anomaly detection becomes an emerging task. Recent studies focus on identifying features of samples leading to abnormal outcomes but cannot recommend a set of actions to flip the abnormal outcomes. In this work, we focus on interpretations via algorithmic recourse that shows how to act to revert abnormal predictions by suggesting actions on features. The key challenge is that algorithmic recourse involves interventions in the physical world, which is fundamentally a causal problem. To tackle this challenge, we propose an interpretable Anomaly Detection framework using Causal Algorithmic Recourse (ADCAR), which recommends recourse actions and infers counterfactual of abnormal samples guided by the causal mechanism. Experiments on three datasets show that ADCAR can flip the abnormal labels with minimal interventions.
translated by 谷歌翻译
可解释的人工智能(XAI)是一系列技术,可以理解人工智能(AI)系统的技术和非技术方面。 Xai至关重要,帮助满足\ emph {可信赖}人工智能的日益重要的需求,其特点是人类自主,防止危害,透明,问责制等的基本特征,反事实解释旨在提供最终用户需要更改的一组特征(及其对应的值)以实现所需的结果。目前的方法很少考虑到实现建议解释所需的行动的可行性,特别是他们缺乏考虑这些行为的因果影响。在本文中,我们将反事实解释作为潜在空间(CEILS)的干预措施,一种方法来生成由数据从数据设计潜在的因果关系捕获的反事实解释,并且同时提供可行的建议,以便到达所提出的配置文件。此外,我们的方法具有以下优点,即它可以设置在现有的反事实发生器算法之上,从而最小化施加额外的因果约束的复杂性。我们展示了我们使用合成和实际数据集的一组不同实验的方法的有效性(包括金融领域的专有数据集)。
translated by 谷歌翻译
多元时间序列中的异常检测在监视各种现实世界系统(例如IT系统运营或制造业)的行为方面起着重要作用。先前的方法对关节分布进行建模,而无需考虑多元时间序列的潜在机制,使它们变得复杂且饥饿。在本文中,我们从因果的角度提出异常检测问题,并将异常视为未遵循常规因果机制来生成多元数据的情况。然后,我们提出了一种基于因果关系的异常检测方法,该方法首先从数据中学习因果结构,然后渗透实例是否是相对于局部因果机制的异常,以从其直接原因产生每个变量,其条件分布可以直接估计从数据。鉴于因果系统的模块化特性,原始问题被分为一系列单独的低维异常检测问题,因此可以直接识别出异常的地方。我们通过模拟和公共数据集以及有关现实世界中AIOPS应用程序的案例研究评估我们的方法,显示其功效,鲁棒性和实际可行性。
translated by 谷歌翻译
反事实推断是一种强大的工具,能够解决备受瞩目的领域中具有挑战性的问题。要进行反事实推断,需要了解潜在的因果机制。但是,仅凭观察和干预措施就不能独特地确定因果机制。这就提出了一个问题,即如何选择因果机制,以便在给定领域中值得信赖。在具有二进制变量的因果模型中已经解决了这个问题,但是分类变量的情况仍未得到解答。我们通过为具有分类变量的因果模型引入反事实排序的概念来应对这一挑战。为了学习满足这些约束的因果机制,并对它们进行反事实推断,我们引入了深层双胞胎网络。这些是深层神经网络,在受过训练的情况下,可以进行双网络反事实推断 - 一种替代绑架,动作和预测方法的替代方法。我们从经验上测试了来自医学,流行病学和金融的多种现实世界和半合成数据的方法,并报告了反事实概率的准确估算,同时证明了反事实订购时不执行反事实的问题。
translated by 谷歌翻译
解决公平问题对于安全使用机器学习算法来支持对人们的生活产生关键影响的决策,例如雇用工作,儿童虐待,疾病诊断,贷款授予等。过去十年,例如统计奇偶校验和均衡的赔率。然而,最新的公平概念是基于因果关系的,反映了现在广泛接受的想法,即使用因果关系对于适当解决公平问题是必要的。本文研究了基于因果关系的公平概念的详尽清单,并研究了其在现实情况下的适用性。由于大多数基于因果关系的公平概念都是根据不可观察的数量(例如干预措施和反事实)来定义的,因此它们在实践中的部署需要使用观察数据来计算或估计这些数量。本文提供了有关从观察数据(包括可识别性(Pearl的SCM框架))和估计(潜在结果框架)中推断出因果量的不同方法的全面报告。该调查论文的主要贡献是(1)指南,旨在在特定的现实情况下帮助选择合适的公平概念,以及(2)根据Pearl的因果关系阶梯的公平概念的排名,表明它很难部署。实践中的每个概念。
translated by 谷歌翻译
算法追求要求为个人提供可操作的建议,以克服自动化决策系统所做的不利结果。求助建议理想地应对个人寻求追索权的特征具有相当小的不确定性。在这项工作中,我们制定了逆势稳健的追索问题,并表明追索方法提供最低售价的追索权无力。然后,我们提出用于在线性和可分辨率案例中产生对抗性稳健追索的方法。为了确保追索权是强劲的,要求个人努力,而不是否则的努力。为了将部分从决策者从决策者转移到决策者的稳健性负担,我们提出了一种模型规范器,鼓励寻求强大追索权的额外成本。我们展示了使用我们提出的模型规范器训练的分类器,依赖于无法解除的预测功能,提供可能更少努力的追索权。
translated by 谷歌翻译
故障诊断在许多领域至关重要,因为故障可能导致安全威胁或经济损失。在在线服务系统领域中,操作员依靠大量监视数据来检测和减轻故障。快速识别一组基础故障的根本原因指标可以节省大量时间减轻故障。在本文中,我们将根本原因分析问题作为一种新的因果推理任务,称为干预识别。我们提出了一种新型的无监督因果推理的方法,名为基于因果推理的根本原因分析(大约)。核心思想是一个足够的条件,可以使监视变量成为根本原因指标,即,因果关系贝叶斯网络(CBN)中父母的概率分布的变化。在在线服务系统中的应用程序中,大约根据系统体系结构的知识和一组因果假设在监视指标中构建图形。仿真研究说明了大约的理论可靠性。现实世界中数据集的性能进一步表明,大约可以将TOP-1建议的回忆提高到最佳基线方法的25%。
translated by 谷歌翻译
已经探索了监督机器学习模型的算法追索问题的问题,以提供决策支持系统中更容易解释,透明和健壮的结果。未开发的区域是用于异常检测的算法求程,特别是仅具有离散特征值的表格数据。这里的问题是提出一组反事实,通过潜在的异常检测模型被认为是正常的,以便应用程序可以将此信息用于解释目的或推荐对策。我们提出了一种方法 - 在表格数据(CARAT)中保留异常算法的背景,该方法是有效,可扩展性且不可知的,对基础异常检测模型。 Carat使用基于变压器的编码器模型来通过查找可能性低的特征来解释异常。随后使用异常实例中特征的整体上下文来修改突出显示的功能,从而生成语义相干的反事实。广泛的实验有助于证明克拉的功效。
translated by 谷歌翻译
在智能交通系统中,交通拥堵异常检测至关重要。运输机构的目标有两个方面:监视感兴趣领域的一般交通状况,并在异常拥堵状态下定位道路细分市场。建模拥塞模式可以实现这些目标,以实现全市道路的目标,相当于学习多元时间序列(MTS)的分布。但是,现有作品要么不可伸缩,要么无法同时捕获MTS中的空间信息。为此,我们提出了一个由数据驱动的生成方法组成的原则性和全面的框架,该方法可以执行可拖动的密度估计来检测流量异常。我们的方法在特征空间中的第一群段段,然后使用条件归一化流以在无监督的设置下在群集级别识别异常的时间快照。然后,我们通过在异常群集上使用内核密度估计器来识别段级别的异常。关于合成数据集的广泛实验表明,我们的方法在召回和F1得分方面显着优于几种最新的拥塞异常检测和诊断方法。我们还使用生成模型来采样标记的数据,该数据可以在有监督的环境中训练分类器,从而减轻缺乏在稀疏设置中进行异常检测的标记数据。
translated by 谷歌翻译
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes. To evaluate the actionability of counterfactuals, we provide metrics that enable comparison of counterfactual-based methods to other local explanation methods. We further address necessary tradeoffs and point to causal implications in optimizing for counterfactuals. Our experiments on four real-world datasets show that our framework can generate a set of counterfactuals that are diverse and well approximate local decision boundaries, outperforming prior approaches to generating diverse counterfactuals. We provide an implementation of the framework at https://github.com/microsoft/DiCE. CCS CONCEPTS• Applied computing → Law, social and behavioral sciences.
translated by 谷歌翻译
Causal learning has attracted much attention in recent years because causality reveals the essential relationship between things and indicates how the world progresses. However, there are many problems and bottlenecks in traditional causal learning methods, such as high-dimensional unstructured variables, combinatorial optimization problems, unknown intervention, unobserved confounders, selection bias and estimation bias. Deep causal learning, that is, causal learning based on deep neural networks, brings new insights for addressing these problems. While many deep learning-based causal discovery and causal inference methods have been proposed, there is a lack of reviews exploring the internal mechanism of deep learning to improve causal learning. In this article, we comprehensively review how deep learning can contribute to causal learning by addressing conventional challenges from three aspects: representation, discovery, and inference. We point out that deep causal learning is important for the theoretical extension and application expansion of causal science and is also an indispensable part of general artificial intelligence. We conclude the article with a summary of open issues and potential directions for future work.
translated by 谷歌翻译
元学习用于通过组合数据和先验知识来有效地自动选择机器学习模型。由于传统的元学习技术缺乏解释性,并且在透明度和公平性方面存在缺点,因此实现元学习的解释性至关重要。本文提出了一个可解释的元学习框架,该框架不仅可以解释元学习算法选择的建议结果,而且还可以对建议算法在特定数据集中的性能和业务场景中更完整,更准确地解释。通过广泛的实验证明了该框架的有效性和正确性。
translated by 谷歌翻译
因果表示学习是识别基本因果变量及其从高维观察(例如图像)中的关系的任务。最近的工作表明,可以从观测的时间序列中重建因果变量,假设它们之间没有瞬时因果关系。但是,在实际应用中,我们的测量或帧速率可能比许多因果效应要慢。这有效地产生了“瞬时”效果,并使以前的可识别性结果无效。为了解决这个问题,我们提出了ICITRI,这是一种因果表示学习方法,当具有已知干预目标的完美干预措施时,可以在时间序列中处理瞬时效应。 Icitris从时间观察中识别因果因素,同时使用可区分的因果发现方法来学习其因果图。在三个视频数据集的实验中,Icitris准确地识别了因果因素及其因果图。
translated by 谷歌翻译
A significant body of research in the data sciences considers unfair discrimination against social categories such as race or gender that could occur or be amplified as a result of algorithmic decisions. Simultaneously, real-world disparities continue to exist, even before algorithmic decisions are made. In this work, we draw on insights from the social sciences brought into the realm of causal modeling and constrained optimization, and develop a novel algorithmic framework for tackling pre-existing real-world disparities. The purpose of our framework, which we call the "impact remediation framework," is to measure real-world disparities and discover the optimal intervention policies that could help improve equity or access to opportunity for those who are underserved with respect to an outcome of interest. We develop a disaggregated approach to tackling pre-existing disparities that relaxes the typical set of assumptions required for the use of social categories in structural causal models. Our approach flexibly incorporates counterfactuals and is compatible with various ontological assumptions about the nature of social categories. We demonstrate impact remediation with a hypothetical case study and compare our disaggregated approach to an existing state-of-the-art approach, comparing its structure and resulting policy recommendations. In contrast to most work on optimal policy learning, we explore disparity reduction itself as an objective, explicitly focusing the power of algorithms on reducing inequality.
translated by 谷歌翻译
A new Lossy Causal Temporal Convolutional Neural Network Autoencoder for anomaly detection is proposed in this work. Our framework uses a rate-distortion loss and an entropy bottleneck to learn a compressed latent representation for the task. The main idea of using a rate-distortion loss is to introduce representation flexibility that ignores or becomes robust to unlikely events with distinctive patterns, such as anomalies. These anomalies manifest as unique distortion features that can be accurately detected in testing conditions. This new architecture allows us to train a fully unsupervised model that has high accuracy in detecting anomalies from a distortion score despite being trained with some portion of unlabelled anomalous data. This setting is in stark contrast to many of the state-of-the-art unsupervised methodologies that require the model to be only trained on "normal data". We argue that this partially violates the concept of unsupervised training for anomaly detection as the model uses an informed decision that selects what is normal from abnormal for training. Additionally, there is evidence to suggest it also effects the models ability at generalisation. We demonstrate that models that succeed in the paradigm where they are only trained on normal data fail to be robust when anomalous data is injected into the training. In contrast, our compression-based approach converges to a robust representation that tolerates some anomalous distortion. The robust representation achieved by a model using a rate-distortion loss can be used in a more realistic unsupervised anomaly detection scheme.
translated by 谷歌翻译
改变特定特征但不是其他特性的输入扰动的反事实示例 - 已经显示用于评估机器学习模型的偏差,例如,对特定的人口组。然而,由于图像的各种特征上的底层的因果结构,生成用于图像的反事实示例是非琐碎的。为了有意义,生成的扰动需要满足因果模型所暗示的约束。我们通过在前瞻性学习推断(ALI)的改进变型中结合结构因果模型(SCM)来提出一种方法,该方法是根据图像的属性之间的因果关系生成反事实。基于所生成的反事实,我们展示了如何解释预先训练的机器学习分类器,评估其偏置,并使用反事实程序缓解偏差。在Morpho-Mnist DataSet上,我们的方法会在质量上产生与基于SCM的Factficuls(DeepScm)的质量相当的反功能,而在更复杂的Celeba DataSet上,我们的方法优于DeepScm在产生高质量的有效反应性时。此外,生成的反事件难以从人类评估实验中的重建图像中无法区分,并且随后使用它们来评估在Celeba数据上培训的标准分类器的公平性。我们表明分类器是偏见的w.r.t.皮肤和头发颜色,以及反事实规则化如何消除这些偏差。
translated by 谷歌翻译
公平机器学习旨在减轻模型预测的偏见,这对于关于诸如种族和性别等敏感属性的某些群体的偏见。在许多现有的公平概念中,反事实公平通过比较来自原始数据和反事实的预测来衡量因因果角度来源的模型公平。在反事实上,该个人的敏感属性值已被修改。最近,少数作品将反事实公平扩展到图数据,但大多数忽略了可能导致偏差的以下事实:1)每个节点邻居的敏感属性可能会影响预测w.r.t.这个节点; 2)敏感属性可能会导致其他特征和图形结构。为了解决这些问题,在本文中,我们提出了一种新颖的公平概念 - 图形反应性公平,这考虑了上述事实领导的偏差。要学习对图形反事实公平的节点表示,我们提出了一种基于反事实数据增强的新颖框架。在此框架中,我们生成对应于每个节点和邻居敏感属性的扰动的反应性。然后,我们通过最大限度地减少从原始图表中学到的表示与每个节点的反事实之间的差异来执行公平性。合成和真实图的实验表明,我们的框架优于图形反事实公平性的最先进的基线,并且还实现了可比的预测性能。
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
可说明的机器学习(ML)近年来由于许多部门的ML基系统的增加而增加了近年来。算法refurrses(ARS)提供“如果输入数据点为x'而不是x的形式的反馈,那么基于ML的系统的输出将是Y'而不是Y.”由于其可行的反馈,对现有的法律框架和忠诚于底层ML模型,ARS由于其可行的反馈而具有吸引力。然而,当前的AR方法是单次拍摄 - 也就是说,它们假设X可以在单个时间段内更改为X'。我们提出了一种新的基于随机控制的方法,它产生序贯ARS,即允许X随机X移动到最终状态X'的ARS。我们的方法是模型不可知论和黑匣子。此外,ARS的计算被摊销,使得一旦训练,它适用于多个DataPoints,而无需重新优化。除了这些主要特征之外,我们的方法还承认可选的Desiderata,例如遵守数据歧管,尊重因果关系和稀疏性 - 通过过去的研究确定的ARS的理想性质。我们使用三个现实世界数据集评估我们的方法,并表现出尊重其他追索者的顺序ARS的成功生成。
translated by 谷歌翻译
随着人工智能的兴起,算法已经变得更好地从培训数据中学习基本模式,包括基于性别,种族等基于性别的社会偏见。部署此类算法对招聘,医疗保健,执法等领域的部署已经提高了严重的领域。对机器学习算法中的公平,问责制,信任和解释性的关注。为了减轻这个问题,我们提出了D-Bias,这是一种视觉交互式工具,它体现了人类在循环AI方法,以审核和减轻表格数据集的社交偏见。它使用图形因果模型来表示数据集中不同特征之间的因果关系,并作为注入域知识的媒介。用户可以通过识别因果网络中的不公平因果关系并使用一系列公平指标来检测对群体(例如女性或亚组)的偏见。此后,用户可以通过在不公平的因果边缘作用来减轻偏见。对于每种相互作用,例如弱化/删除有偏见的因果边缘,系统使用一种新方法来模拟基于当前因果模型的新(cla依)数据集。用户可以在视觉上评估其相互作用对不同公平指标,公用事业指标,数据失真和基础数据分布的影响。一旦满足,他们就可以下载依据的数据集并将其用于任何下游应用程序以进行更公正的预测。我们通过对3个数据集进行实验以及一项正式的用户研究来评估D偏差。我们发现,与不同公平指标的基线偏差方法相比,D偏差有助于显着降低偏差,同时几乎没有数据失真和效用较小的损失。此外,我们基于人类的方法极大地超过了关于信任,解释性和问责制的自动方法。
translated by 谷歌翻译