A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using counterfactual examples has been empirically shown to break spurious correlations. However, the counterfactual generation task itself becomes more difficult as the level of confounding increases. Existing methods for counterfactual generation under confounding consider a fixed set of interventions (e.g., texture, rotation) and are not flexible enough to capture diverse data-generating processes. Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors. To minimize such correlation, we propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes, even when the dataset is highly confounded. These counterfactual images are then used to regularize the downstream classifier such that the learned representations are the same across various generative factors conditioned on the class label. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables. Our experimental results on both synthetic (MNIST variants) and real-world (CelebA) datasets show the usefulness of our approach.
translated by 谷歌翻译
Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the same distribution. However, this assumption seldom holds in the real world due to distribution shifts. As a result models that rely on this assumption exhibit poor generalization capabilities. Over the recent years, dedicated efforts have been made to improve the generalization capabilities of these models collectively known as -- \textit{domain generalization methods}. The primary idea behind these methods is to identify stable features or mechanisms that remain invariant across the different distributions. Many generalization approaches employ causal theories to describe invariance since causality and invariance are inextricably intertwined. However, current surveys deal with the causality-aware domain generalization methods on a very high-level. Furthermore, we argue that it is possible to categorize the methods based on how causality is leveraged in that method and in which part of the model pipeline is it used. To this end, we categorize the causal domain generalization methods into three categories, namely, (i) Invariance via Causal Data Augmentation methods which are applied during the data pre-processing stage, (ii) Invariance via Causal representation learning methods that are utilized during the representation learning stage, and (iii) Invariance via Transferring Causal mechanisms methods that are applied during the classification stage of the pipeline. Furthermore, this survey includes in-depth insights into benchmark datasets and code repositories for domain generalization methods. We conclude the survey with insights and discussions on future directions.
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
代表学习者认为,解开变异的因素已经证明是在解决各种现实世界的关切方面是重要的,如公平和可意识。最初由具有独立假设的无监督模型组成,最近,监督和相关特征较弱,但没有生成过程的因果关系。相比之下,我们在原因生成过程的制度下工作,因为生成因子是独立的,或者可能被一组观察或未观察到的混乱困惑。我们通过解散因果过程的概念对解开表示的分析。我们激励对新指标和数据集进行研究,以研究因果解剖和提出两个评估指标和数据集。我们展示了我们的指标捕获了解开了因果过程的探索。最后,我们利用我们的指标和数据集对艺术艺术状态的实证研究进行了脱扣代表学习者,以从因果角度来评估它们。
translated by 谷歌翻译
神经网络利用数据中的因果关系和相关的关系,以学习优化给定性能标准的模型,例如分类准确性。这导致学习模型可能不一定反映输入和输出之间的真实因果关系。当在培训时可获得因果关系的域中,即使在学习优化性能标准时,神经网络模型也将这些关系保持为因果关系。我们提出了一种因果规则化方法,可以将这种因果域前瞻纳入网络,并支持直接和完全因果效应。我们表明这种方法可以推广到各种因果前导者的规范,包括给定输入特征的因果效果的单调性或针对公平的目的去除一定的影响。我们在11个基准数据集上的实验显示了这种方法在规则中规范学习的神经网络模型以保持所需的因果效果。在大多数数据集上,可以在不损害精度的情况下获得域名一致模型。
translated by 谷歌翻译
机器学习模型被批评反映了培训数据中的不公平偏见。我们通过直接引入公平的学习算法来解决这一目标,而不是通过介绍公平的学习算法来解决公平的合成数据,使任何下游学习者都是公平的。从不公平数据生成公平的合成数据 - 同时对潜在的数据生成过程(DGP)留下真实 - 是非微不足道的。在本文中,我们引入了Decaf:用于表格数据的GaN的公平合成数据发生器。通过Decaf,我们将DGP显式作为发电机的输入层中的结构因果模型嵌入,允许在其因果父母上重建每个变量。此过程启用推理时间扩大,其中可以策略性地删除偏置边缘以满足用户定义的公平要求。 Decaf框架是多功能的,与几个公平的定义兼容。在我们的实验中,我们表明Decaf成功地消除了不希望的偏见和 - 与现有方法相比 - 能够产生高质量的合成数据。此外,我们为发电机的收敛和下游模型的公平提供理论担保。
translated by 谷歌翻译
变异因素之间的相关性在现实数据中普遍存在。机器学习算法可能会受益于利用这种相关性,因为它们可以提高噪声数据的预测性能。然而,通常这种相关性不稳定(例如,它们可能在域,数据集或应用程序之间发生变化),我们希望避免利用它们。解剖学方法旨在学习捕获潜伏子空间变化不同因素的表示。常用方法涉及最小化潜伏子空间之间的相互信息,使得每个潜在的底层属性。但是,当属性相关时,这会失败。我们通过强制执行可用属性上的子空间之间的独立性来解决此问题,这允许我们仅删除不导致的依赖性,这些依赖性是由于训练数据中存在的相关结构。我们通过普发的方法实现这一目标,以最小化关于分类变量的子空间之间的条件互信息(CMI)。我们首先在理论上展示了CMI最小化是对高斯数据线性问题的稳健性解剖的良好目标。然后,我们基于MNIST和Celeba在现实世界数据集上应用我们的方法,并表明它会在相关偏移下产生脱屑和强大的模型,包括弱监督设置。
translated by 谷歌翻译
Trying to capture the sample-label relationship, conditional generative models often end up inheriting the spurious correlation in the training dataset, giving label-conditional distributions that are severely imbalanced in another latent attribute. To mitigate such undesirable correlations engraved into generative models, which we call spurious causality, we propose a general two-step strategy. (a) Fairness Intervention (FI): Emphasize the minority samples that are hard to be generated due to the spurious correlation in the training dataset. (b) Corrective Sampling (CS): Filter the generated samples explicitly to follow the desired label-conditional latent attribute distribution. We design the fairness intervention for various degrees of supervision on the spurious attribute, including unsupervised, weakly-supervised, and semi-supervised scenarios. Our experimental results show that the proposed FICS can successfully resolve the spurious correlation in generated samples on various datasets.
translated by 谷歌翻译
本文提出了在适当的监督信息下进行分解的生成因果代表(亲爱的)学习方法。与实施潜在变量独立性的现有分解方法不同,我们考虑了一种基本利益因素可以因果关系相关的一般情况。我们表明,即使在监督下,先前具有独立先验的方法也无法解散因果关系。在这一发现的激励下,我们提出了一种称为DEAR的新的解开学习方法,该方法可以使因果可控的产生和因果代表学习。这种新公式的关键要素是使用结构性因果模型(SCM)作为双向生成模型的先验分布。然后,使用合适的GAN算法与发电机和编码器共同训练了先验,并与有关地面真相因子及其基本因果结构的监督信息合并。我们提供了有关该方法的可识别性和渐近收敛性的理论理由。我们对合成和真实数据集进行了广泛的实验,以证明DEAR在因果可控生成中的有效性,以及在样本效率和分布鲁棒性方面,学到的表示表示对下游任务的好处。
translated by 谷歌翻译
分发班次的稳健性对于部署现实世界中的机器学习模型至关重要。尽管如此必要的,但在定义导致这些变化的潜在机制以及评估跨多个不同的分发班次的稳健性的潜在机制很少。为此,我们介绍了一种框架,可实现各种分布换档的细粒度分析。我们通过评估在合成和现实世界数据集中分为五个类别的19个不同的方法来提供对当前最先进的方法的整体分析。总的来说,我们训练超过85架模型。我们的实验框架可以很容易地扩展到包括新方法,班次和数据集。我们发现,与以前的工作〜\ citep {gulrajani20}不同,该进度已经通过标准的ERM基线进行;特别是,在许多情况下,预先训练和增强(学习或启发式)提供了大的收益。但是,最好的方法在不同的数据集和班次上不一致。
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
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model's sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anticausal elements. We motivate this approach, Risk Extrapolation (REx), as a form of robust optimization over a perturbation set of extrapolated domains (MM-REx), and propose a penalty on the variance of training risks (V-REx) as a simpler variant. We prove that variants of REx can recover the causal mechanisms of the targets, while also providing some robustness to changes in the input distribution ("covariate shift"). By tradingoff robustness to causally induced distributional shifts and covariate shift, REx is able to outperform alternative methods such as Invariant Risk Minimization in situations where these types of shift co-occur.
translated by 谷歌翻译
鉴于部署更可靠的机器学习系统的重要性,研究界内的机器学习模型的解释性得到了相当大的关注。在计算机视觉应用中,生成反事实方法表示如何扰乱模型的输入来改变其预测,提供有关模型决策的详细信息。目前的方法倾向于产生关于模型决策的琐碎的反事实,因为它们通常建议夸大或消除所分类的属性的存在。对于机器学习从业者,这些类型的反事件提供了很少的价值,因为它们没有提供有关不期望的模型或数据偏差的新信息。在这项工作中,我们确定了琐碎的反事实生成问题,我们建议潜水以缓解它。潜水在使用多样性强制损失限制的解除印章潜在空间中学习扰动,以发现关于模型预测的多个有价值的解释。此外,我们介绍一种机制,以防止模型产生微不足道的解释。 Celeba和Synbols的实验表明,与先前的最先进的方法相比,我们的模型提高了生产高质量有价值解释的成功率。代码可在https://github.com/elementai/beyond- trial-explanations获得。
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
从多个域收集的现实世界数据可以在多个属性上具有多个不同的分布变化。但是,域概括(DG)算法的最新进展仅关注对单个属性的特定变化。我们介绍了具有多属性分布变化的数据集,并发现现有的DG算法无法概括。为了解释这一点,我们使用因果图来根据虚假属性与分类标签之间的关系来表征不同类型的变化。每个多属性因果图都需要对观察到的变量进行不同的约束,因此,基于单个固定独立性约束的任何算法都不能在所有变化中正常工作。我们提出了因果自适应约束最小化(CACM),这是一种用于识别正则化的正确独立性约束的新算法。完全合成,MNIST和小型NORB数据集的结果,涵盖了二进制和多价值属性和标签,确认我们的理论主张:正确的独立性约束导致未见域的最高准确性,而不正确的约束则无法做到这一点。我们的结果表明,建模数据生成过程中固有的因果关系的重要性:在许多情况下,如果没有此信息,就不可能知道正确的正规化约束。
translated by 谷歌翻译
我们通过对杂散相关性的因果解释提出了一种信息 - 理论偏置测量技术,这通过利用条件相互信息来识别特征级算法偏压有效。尽管已经提出了几种偏置测量方法并广泛地研究以在各种任务中实现诸如面部识别的各种任务中的算法公平,但它们的准确性或基于Logit的度量易于导致普通预测得分调整而不是基本偏差减少。因此,我们设计针对算法偏差的新型扩张框架,其包括由所提出的信息 - 理论偏置测量方法导出的偏压正则化损耗。此外,我们介绍了一种基于随机标签噪声的简单而有效的无监督的脱叠技术,这不需要明确的偏置信息监督。通过多种标准基准测试的广泛实验,在不同的现实情景中验证了所提出的偏差测量和脱叠方法。
translated by 谷歌翻译
尽管无偏见的机器学习模型对于许多应用程序至关重要,但偏见是一个人为定义的概念,可以在任务中有所不同。只有输入标签对,算法可能缺乏足够的信息来区分稳定(因果)特征和不稳定(虚假)特征。但是,相关任务通常具有类似的偏见 - 我们可以利用在转移环境中开发稳定的分类器的观察结果。在这项工作中,我们明确通知目标分类器有关源任务中不稳定功能的信息。具体而言,我们得出一个表示,该表示通过对比源任务中的不同数据环境来编码不稳定的功能。我们通过根据此表示形式将目标任务的数据聚类来实现鲁棒性,并最大程度地降低这些集群中最坏情况的风险。我们对文本和图像分类进行评估。经验结果表明,我们的算法能够在合成生成的环境和现实环境的目标任务上保持鲁棒性。我们的代码可在https://github.com/yujiabao/tofu上找到。
translated by 谷歌翻译
尽管它们的准确性很高,但由于未知的决策过程和潜在的偏见,现代复杂的图像分类器不能被敏感任务受到信任。反事实解释非常有效地为这些黑盒算法提供透明度。然而,生成可能对分类器输出产生一致影响并揭示可解释的特征更改的反事实是一项非常具有挑战性的任务。我们介绍了一种新颖的方法,可以使用验证的生成模型为图像分类器生成因果关系但可解释的反事实解释,而无需进行任何重新训练或调节。该技术中的生成模型不可能在与目标分类器相同的数据上进行训练。我们使用此框架来获得对比度和因果关系,并作为黑盒分类器的全球解释。在面部属性分类的任务上,我们通过提供因果和对比特征属性以及相应的反事实图像来展示不同属性如何影响分类器输出。
translated by 谷歌翻译
我们描述了Countersynth,一种诱导标签驱动的扩散变形的条件生成模型,体积脑图像中的标签驱动的生物合理的变化。该模型旨在综合用于下游判别判断性建模任务的反事实训练数据,其中保真度受数据不平衡,分布不稳定性,混淆或缺点的限制,并且在不同的群体中表现出不公平的性能。专注于人口统计属性,我们评估了具有基于体素的形态学,分类和回归条件属性的合成反事实的质量,以及FR \'{e} CHET开始距离。在设计的人口统计不平衡和混淆背景下检查下游歧视性能,我们使用英国Biobank磁共振成像数据来基准测试对这些问题的当前解决方案的增强。我们实现了最先进的改进,无论是整体忠诚和股权。 CounterSynth的源代码可在线获取。
translated by 谷歌翻译
使用适当的电感偏差,反事实生成网络(CGN)可以从形状,纹理和背景歧管的随机组合中生成新图像。这些图像可以用于训练不变的分类器,避免了深层体系结构学习虚假相关性而不是有意义的问题。结果,改善了室外鲁棒性。但是,CGN体系结构包括多个参数化网络,即BigGan和U2-NET。培训这些网络需要适当的背景知识和广泛的计算。由于一个人并不总是能够访问精确的培训细节,也不总是拥有反事实的必要知识,因此我们的工作解决了以下问题:我们可以使用预先训练的CGN中嵌入的知识来培训低容量的模型,假设对架构组件的黑框访问(即仅访问验证的CGN模型)?在这个方向上,我们提出了一项名为SKDCGN的新颖作品,该作品尝试使用知识蒸馏(KD)尝试知识转移。在我们提出的架构中,每个独立的机制(形状,纹理,背景)都由一个学生“ tinygan”代表,该学生从预验证的老师“ Biggan”中学习。我们通过使用KD和适当的损失函数来证明使用最先进的数据集(例如ImageNet)和MNIST的疗效。此外,作为另一项贡献,我们的论文对CGN的组成机制进行了详尽的研究,以更好地了解每种机制如何影响不变分类器的分类精度。代码可用:https://github.com/ambekarsameer96/skdcgn
translated by 谷歌翻译