数据清洁通常包括离群检测和数据修复。系统错误是由于数据反复发生的几乎确定性转换而导致的，例如特定的图像像素设置为默认值或水印。因此，容量足够的模型很容易地超出这些错误，从而使检测和修复变得困难。作为系统的离群值是干净实例和系统误差模式的模式的组合，我们的主要见解是，嵌入者可以通过模型中的较小的表示形式（子空间）来建模，而不是离群值。通过利用这一点，我们提出了清洁子空间变量自动编码器（CLSVAE），这是一种新型的半监督模型，用于检测和自动修复系统误差。主要思想是分别分别分区潜在的空间和模型模型。与以前的相关模型相比，CLSVAE的有效数据少得多，通常不到2％的数据。我们在具有不同级别的损坏和标记的集合大小的方案中使用三个图像数据集提供实验，与相关基线相比。 CLSVAE提供了无人干预的优质维修，例如与最接近的基线相比，只有标记数据的0.25％的相对误差下降了58％。

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate the β-TCVAE (Total Correlation Variational Autoencoder) algorithm, a refinement and plug-in replacement of the β-VAE for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the model is trained using our framework.

We present a principled approach to incorporating labels in VAEs that captures the rich characteristic information associated with those labels. While prior work has typically conflated these by learning latent variables that directly correspond to label values, we argue this is contrary to the intended effect of supervision in VAEs-capturing rich label characteristics with the latents. For example, we may want to capture the characteristics of a face that make it look young, rather than just the age of the person. To this end, we develop the CCVAE, a novel VAE model and concomitant variational objective which captures label characteristics explicitly in the latent space, eschewing direct correspondences between label values and latents. Through judicious structuring of mappings between such characteristic latents and labels, we show that the CCVAE can effectively learn meaningful representations of the characteristics of interest across a variety of supervision schemes. In particular, we show that the CCVAE allows for more effective and more general interventions to be performed, such as smooth traversals within the characteristics for a given label, diverse conditional generation, and transferring characteristics across datapoints.

在异常检测（AD）中，给出了识别测试样本是否异常，给出了正常样本的数据集。近期和有希望的广告方法依赖于深度生成模型，例如变形自动化器（VAES），用于对正常数据分布的无监督学习。在半监督广告（SSAD）中，数据还包括标记异常的小样本。在这项工作中，我们提出了两个用于SSAD培训VAES的两个变分方法。两种方法中的直观思路是将编码器训练到潜在向量之间的“分开”以进行正常和异常数据。我们表明，这个想法可以源于问题的原则概率制剂，并提出了简单有效的算法。我们的方法可以应用于各种数据类型，因为我们在从自然图像到天文学和医学的SSAD数据集上展示，可以与任何VAE模型架构相结合，并且自然与合奏相兼容。与未特定于特定数据类型的最先进的SSAD方法比较时，我们获得了异常值检测的显着改进。

We explore an original strategy for building deep networks, based on stacking layers of denoising autoencoders which are trained locally to denoise corrupted versions of their inputs. The resulting algorithm is a straightforward variation on the stacking of ordinary autoencoders. It is however shown on a benchmark of classification problems to yield significantly lower classification error, thus bridging the performance gap with deep belief networks (DBN), and in several cases surpassing it. Higher level representations learnt in this purely unsupervised fashion also help boost the performance of subsequent SVM classifiers. Qualitative experiments show that, contrary to ordinary autoencoders, denoising autoencoders are able to learn Gabor-like edge detectors from natural image patches and larger stroke detectors from digit images. This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challenge some common assumptions. We first theoretically show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data. Then, we train more than 12 000 models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets. We observe that while the different methods successfully enforce properties "encouraged" by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Furthermore, increased disentanglement does not seem to lead to a decreased sample complexity of learning for downstream tasks. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets.

当前独立于域的经典计划者需要问题域和实例作为输入的符号模型，从而导致知识采集瓶颈。同时，尽管深度学习在许多领域都取得了重大成功，但知识是在与符号系统（例如计划者）不兼容的亚符号表示中编码的。我们提出了Latplan，这是一种无监督的建筑，结合了深度学习和经典计划。只有一组未标记的图像对，显示了环境中允许的过渡子集（训练输入），Latplan学习了环境的完整命题PDDL动作模型。稍后，当给出代表初始状态和目标状态（计划输入）的一对图像时，Latplan在符号潜在空间中找到了目标状态的计划，并返回可视化的计划执行。我们使用6个计划域的基于图像的版本来评估LATPLAN：8个插头，15个式嘴，Blockworld，Sokoban和两个LightsOut的变体。

主体组件分析（PCA）在给定固定组件维度的一类线性模型的情况下，将重建误差最小化。概率PCA通过学习PCA潜在空间权重的概率分布，从而创建生成模型，从而添加了概率结构。自动编码器（AE）最小化固定潜在空间维度的一类非线性模型中的重建误差，在固定维度处胜过PCA。在这里，我们介绍了概率自动编码器（PAE），该自动编码器（PAE）使用归一化流量（NF）了解了AE潜在空间权重的概率分布。 PAE快速且易于训练，并在下游任务中遇到小的重建错误，样本质量高以及良好的性能。我们将PAE与差异AE（VAE）进行比较，表明PAE训练更快，达到较低的重建误差，并产生良好的样品质量，而无需特殊的调整参数或培训程序。我们进一步证明，PAE是在贝叶斯推理的背景下，用于涂抹和降解应用程序的贝叶斯推断，可以执行概率图像重建的下游任务的强大模型。最后，我们将NF的潜在空间密度确定为有希望的离群检测度量。

异常检测是指识别偏离正常模式的观察，这是各个领域的活跃研究区域。最近，数据量表越来越多，复杂性和维度将传统的表示和基于统计的异常检测方法变得具有挑战性。在本文中，我们利用了高光谱图像异常检测的生成模型。 GIST是模拟正常数据的分布，而分布外样品可以被视为异常值。首先，研究了基于变分的基于异常的检测方法。理论上和经验地发现它们由于距离强烈的概念（$ F $ -divergence）作为正则化而不稳定。其次，本文介绍了切片的Wasserstein距离，与F分歧相比，这是一种较弱的分布措施。然而，随机切片的数量难以估计真正的距离。最后，我们提出了一个投影的切片Wasserstein（PSW）基于AutoEncoder的异常筛选方法。特别是，我们利用计算友好的特征分解方法来找到切片高维数据的主成分。此外，我们所提出的距离可以用闭合形式计算，即使是先前的分布也不是高斯。在各种现实世界高光谱异常检测基准上进行的综合实验证明了我们提出的方法的卓越性能。

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。

带有变异自动编码器（VAE）的学习分解表示通常归因于损失的正则化部分。在这项工作中，我们强调了数据与损失的重建项之间的相互作用，这是VAE中解散的主要贡献者。我们注意到，标准化的基准数据集的构建方式有利于学习似乎是分解的表示形式。我们设计了一个直观的对抗数据集，该数据集利用这种机制破坏了现有的最新分解框架。最后，我们提供了一种解决方案，可以通过修改重建损失来实现分离，从而影响VAES如何感知数据点之间的距离。

机器学习模型通常会遇到与训练分布不同的样本。无法识别分布（OOD）样本，因此将该样本分配给课堂标签会显着损害模​​型的可靠性。由于其对在开放世界中的安全部署模型的重要性，该问题引起了重大关注。由于对所有可能的未知分布进行建模的棘手性，检测OOD样品是具有挑战性的。迄今为止，一些研究领域解决了检测陌生样本的问题，包括异常检测，新颖性检测，一级学习，开放式识别识别和分布外检测。尽管有相似和共同的概念，但分别分布，开放式检测和异常检测已被独立研究。因此，这些研究途径尚未交叉授粉，创造了研究障碍。尽管某些调查打算概述这些方法，但它们似乎仅关注特定领域，而无需检查不同领域之间的关系。这项调查旨在在确定其共同点的同时，对各个领域的众多著名作品进行跨域和全面的审查。研究人员可以从不同领域的研究进展概述中受益，并协同发展未来的方法。此外，据我们所知，虽然进行异常检测或单级学习进行了调查，但没有关于分布外检测的全面或最新的调查，我们的调查可广泛涵盖。最后，有了统一的跨域视角，我们讨论并阐明了未来的研究线，打算将这些领域更加紧密地融为一体。

近年来，由于其对复杂分布进行建模的能力，深层生成模型引起了越来越多的兴趣。在这些模型中，变异自动编码器已被证明是计算有效的，并且在多个领域中产生了令人印象深刻的结果。在这一突破之后，为了改善原始出版物而进行了广泛的研究，从而导致各种不同的VAE模型响应不同的任务。在本文中，我们介绍了Pythae，这是一个多功能的开源Python库，既可以提供统一的实现和专用框架，允许直接，可重现且可靠地使用生成自动编码器模型。然后，我们建议使用此库来执行案例研究基准测试标准，在其中我们介绍并比较了19个生成自动编码器模型，代表了下游任务的一些主要改进，例如图像重建，生成，分类，聚类，聚类和插值。可以在https://github.com/clementchadebec/benchmark_vae上找到开源库。

变化自动编码器（VAE）最近已用于对复杂密度分布的无监督分离学习。存在许多变体，以鼓励潜在空间中的分解，同时改善重建。但是，在达到极低的重建误差和高度分离得分之间，没有人同时管理权衡。我们提出了一个普遍的框架，可以在有限的优化下应对这一挑战，并证明它在平衡重建时，它优于现有模型的最先进模型。我们介绍了三个可控的拉格朗日超级参数，以控制重建损失，KL差异损失和相关度量。我们证明，重建网络中的信息最大化等于在合理假设和约束放松下摊销过程中的信息最大化。

We present a detailed study on Variational Autoencoders (VAEs) for anomalous jet tagging at the Large Hadron Collider. By taking in low-level jet constituents' information, and training with background QCD jets in an unsupervised manner, the VAE is able to encode important information for reconstructing jets, while learning an expressive posterior distribution in the latent space. When using the VAE as an anomaly detector, we present different approaches to detect anomalies: directly comparing in the input space or, instead, working in the latent space. In order to facilitate general search approaches such as bump-hunt, mass-decorrelated VAEs based on distance correlation regularization are also studied. We find that the naive mass-decorrelated VAEs fail at maintaining proper detection performance, by assigning higher probabilities to some anomalous samples. To build a performant mass-decorrelated anomalous jet tagger, we propose the Outlier Exposed VAE (OE-VAE), for which some outlier samples are introduced in the training process to guide the learned information. OE-VAEs are employed to achieve two goals at the same time: increasing sensitivity of outlier detection and decorrelating jet mass from the anomaly score. We succeed in reaching excellent results from both aspects. Code implementation of this work can be found at https://github.com/taolicheng/VAE-Jet

A grand goal in deep learning research is to learn representations capable of generalizing across distribution shifts. Disentanglement is one promising direction aimed at aligning a models representations with the underlying factors generating the data (e.g. color or background). Existing disentanglement methods, however, rely on an often unrealistic assumption: that factors are statistically independent. In reality, factors (like object color and shape) are correlated. To address this limitation, we propose a relaxed disentanglement criterion - the Hausdorff Factorized Support (HFS) criterion - that encourages a factorized support, rather than a factorial distribution, by minimizing a Hausdorff distance. This allows for arbitrary distributions of the factors over their support, including correlations between them. We show that the use of HFS consistently facilitates disentanglement and recovery of ground-truth factors across a variety of correlation settings and benchmarks, even under severe training correlations and correlation shifts, with in parts over +60% in relative improvement over existing disentanglement methods. In addition, we find that leveraging HFS for representation learning can even facilitate transfer to downstream tasks such as classification under distribution shifts. We hope our original approach and positive empirical results inspire further progress on the open problem of robust generalization.

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.

变异自动编码器（VAE）是最常用的无监督机器学习模型之一。但是，尽管对先前和后验的高斯分布的默认选择通常代表了数学方便的分布通常会导致竞争结果，但我们表明该参数化无法用潜在的超球体结构对数据进行建模。为了解决这个问题，我们建议使用von Mises-fisher（VMF）分布，从而导致超级潜在空间。通过一系列实验，我们展示了这种超球vae或$ \ mathcal {s} $ - vae如何更适合于用超球形结构捕获数据，同时胜过正常的，$ \ mathcal {n} $ - vae-，在其他数据类型的低维度中。http://github.com/nicola-decao/s-vae-tf和https://github.com/nicola-decao/nicola-decao/s-vae-pytorch

我们提出了一种自我监督的方法，以解除高维数据变化的因素，该因素不依赖于基本变化概况的先验知识（例如，没有关于要提取单个潜在变量的数量或分布的假设）。在我们称为nashae的方法中，通过促进从所有其他编码元素中恢复的每个编码元素和恢复的元素的信息之间的差异，在标准自动编码器（AE）的低维潜在空间中完成了高维的特征分离。通过将其作为AE和回归网络合奏之间的Minmax游戏来有效地促进了分解，从而估算了一个元素，该元素以对所有其他元素的观察为条件。我们将我们的方法与使用现有的分离指标进行定量比较。此外，我们表明Nashae具有提高的可靠性和增加的能力来捕获学习潜在表示中的显着数据特征。