Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source domain, can generalize to the target domain. In this paper, we first construct a simple counterexample showing that, contrary to common belief, the above conditions are not sufficient to guarantee successful domain adaptation. In particular, the counterexample exhibits conditional shift: the class-conditional distributions of input features change between source and target domains. To give a sufficient condition for domain adaptation, we propose a natural and interpretable generalization upper bound that explicitly takes into account the aforementioned shift. Moreover, we shed new light on the problem by proving an information-theoretic lower bound on the joint error of any domain adaptation method that attempts to learn invariant representations. Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target. Finally, we conduct experiments on real-world datasets that corroborate our theoretical findings. We believe these insights are helpful in guiding the future design of domain adaptation and representation learning algorithms.
translated by 谷歌翻译
所有著名的机器学习算法构成了受监督和半监督的学习工作,只有在一个共同的假设下:培训和测试数据遵循相同的分布。当分布变化时,大多数统计模型必须从新收集的数据中重建,对于某些应用程序,这些数据可能是昂贵或无法获得的。因此,有必要开发方法,以减少在相关领域中可用的数据并在相似领域中进一步使用这些数据,从而减少需求和努力获得新的标签样品。这引起了一个新的机器学习框架,称为转移学习:一种受人类在跨任务中推断知识以更有效学习的知识能力的学习环境。尽管有大量不同的转移学习方案,但本调查的主要目的是在特定的,可以说是最受欢迎的转移学习中最受欢迎的次级领域,概述最先进的理论结果,称为域适应。在此子场中,假定数据分布在整个培训和测试数据中发生变化,而学习任务保持不变。我们提供了与域适应性问题有关的现有结果的首次最新描述,该结果涵盖了基于不同统计学习框架的学习界限。
translated by 谷歌翻译
Discriminative learning methods for classification perform well when training and test data are drawn from the same distribution. Often, however, we have plentiful labeled training data from a source domain but wish to learn a classifier which performs well on a target domain with a different distribution and little or no labeled training data. In this work we investigate two questions. First, under what conditions can a classifier trained from source data be expected to perform well on target data? Second, given a small amount of labeled target data, how should we combine it during training with the large amount of labeled source data to achieve the lowest target error at test time?
translated by 谷歌翻译
This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain adaptation methods based on adversarial learning. However, several disconnections still exist and form the gap between theory and algorithm. We extend previous theories (Mansour et al., 2009c;Ben-David et al., 2010) to multiclass classification in domain adaptation, where classifiers based on the scoring functions and margin loss are standard choices in algorithm design. We introduce Margin Disparity Discrepancy, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training. Our theory can be seamlessly transformed into an adversarial learning algorithm for domain adaptation, successfully bridging the gap between theory and algorithm. A series of empirical studies show that our algorithm achieves the state of the art accuracies on challenging domain adaptation tasks.
translated by 谷歌翻译
Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. To learn such representations, domain adaptation frameworks usually include a domain invariant representation learning approach to measure and reduce the domain discrepancy, as well as a discriminator for classification. Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WD-GRL). WDGRL utilizes a neural network, denoted by the domain critic, to estimate empirical Wasserstein distance between the source and target samples and optimizes the feature extractor network to minimize the estimated Wasserstein distance in an adversarial manner. The theoretical advantages of Wasserstein distance for domain adaptation lie in its gradient property and promising generalization bound. Empirical studies on common sentiment and image classification adaptation datasets demonstrate that our proposed WDGRL outperforms the state-of-the-art domain invariant representation learning approaches.
translated by 谷歌翻译
在高赌注域中的机器学习工具的实际应用通常被调节为公平,因此预测目标应该满足相对于受保护属性的奇偶校验的一些定量概念。然而,公平性和准确性之间的确切权衡并不完全清楚,即使是对分类问题的基本范式也是如此。在本文中,我们通过在任何公平分类器的群体误差之和中提供较低的界限,在分类设置中表征统计奇偶校验和准确性之间的固有权衡。我们不可能的定理可以被解释为公平的某种不确定性原则:如果基本率不同,那么符合统计奇偶校验的任何公平分类器都必须在至少一个组中产生很大的错误。我们进一步扩展了这一结果,以便在学习公平陈述的角度下给出任何(大约)公平分类者的联合误差的下限。为了表明我们的下限是紧张的,假设Oracle访问贝叶斯(潜在不公平)分类器,我们还构造了一种返回一个随机分类器的算法,这是最佳和公平的。有趣的是,当受保护的属性可以采用超过两个值时,这个下限的扩展不承认分析解决方案。然而,在这种情况下,我们表明,通过解决线性程序,我们可以通过解决我们作为电视 - 重心问题的术语,电视距离的重心问题来有效地计算下限。在上面,我们证明,如果集团明智的贝叶斯最佳分类器是关闭的,那么学习公平的表示导致公平的替代概念,称为准确性奇偶校验,这使得错误率在组之间关闭。最后,我们还在现实世界数据集上进行实验,以确认我们的理论发现。
translated by 谷歌翻译
Discriminative learning methods for classification perform well when training and test data are drawn from the same distribution. In many situations, though, we have labeled training data for a source domain, and we wish to learn a classifier which performs well on a target domain with a different distribution. Under what conditions can we adapt a classifier trained on the source domain for use in the target domain? Intuitively, a good feature representation is a crucial factor in the success of domain adaptation. We formalize this intuition theoretically with a generalization bound for domain adaption. Our theory illustrates the tradeoffs inherent in designing a representation for domain adaptation and gives a new justification for a recently proposed model. It also points toward a promising new model for domain adaptation: one which explicitly minimizes the difference between the source and target domains, while at the same time maximizing the margin of the training set. This situation arises often in machine learning. For example, we might want to adapt for a new user (the target domain) a spam filter trained on the email of a group of previous users (the source domain), under the assumption that users generally agree on what is spam and what is not. Then, the challenge is that the distributions of emails for the first set of users and for the new user are different. Intuitively, one might expect that the closer the two distributions are, the better the filter trained on the source domain will do on the target domain.
translated by 谷歌翻译
无监督域适应(UDA)的绝大多数现有算法都集中在以一次性的方式直接从标记的源域调整到未标记的目标域。另一方面,逐渐的域适应性(GDA)假设桥接源和目标的$(t-1)$未标记的中间域,并旨在通过利用中间的路径在目标域中提供更好的概括。在某些假设下,Kumar等人。 (2020)提出了一种简单的算法,逐渐自我训练,以及按$ e^{o(t)} \ left的顺序结合的概括(\ varepsilon_0+o \ of \ left(\ sqrt {log(log(log(t)/n log(t)/n) } \ right)\ right)$对于目标域错误,其中$ \ varepsilon_0 $是源域错误,$ n $是每个域的数据大小。由于指数因素,当$ t $仅适中时,该上限变得空虚。在这项工作中,我们在更一般和放松的假设下分析了逐步的自我训练,并证明概括为$ \ varepsilon_0 + o \ left(t \ delta + t/\ sqrt {n} {n} \ right) + \ widetilde { o} \ left(1/\ sqrt {nt} \ right)$,其中$ \ delta $是连续域之间的平均分配距离。与对$ t $作为乘法因素的指数依赖性的现有界限相比,我们的界限仅取决于$ t $线性和添加性。也许更有趣的是,我们的结果意味着存在最佳的$ t $的最佳选择,从而最大程度地减少了概括性错误,并且自然也暗示了一种构造中间域路径的最佳方法,以最大程度地减少累积路径长度$ t \ delta源和目标之间的$。为了证实我们理论的含义,我们检查了对多个半合成和真实数据集的逐步自我训练,这证实了我们的发现。我们相信我们的见解为未来GDA算法设计的途径提供了前进的途径。
translated by 谷歌翻译
域适应(DA)从严格的理论作品中获益,研究其富有识别特征和各个方面,例如学习领域 - 不变的表示及其权衡。然而,由于多个源域的参与和训练期间目标域的潜在不可用的域,因此似乎不是这种源DA和域泛化(DG)设置的情况非常复杂和复杂。在本文中,我们为目标一般损失开发了新的上限,吸引我们来定义两种域名不变的表示。我们进一步研究了利弊以及执行学习每个领域不变的表示的权衡。最后,我们进行实验检查这些陈述的权衡,以便在实践中提供有关如何使用它们的实践提示,并探索我们发达理论的其他有趣性质。
translated by 谷歌翻译
无监督的域适应(UDA)通过将知识从标记的源域传送到与目标的分布不同的标记源域来实现跨域学习。但是,UDA并不总是成功,在文献中报告了几个“负转移”的几个账目。在这项工作中,我们在目标域错误上证明了一个简单的下限,这些错误符合现有的上限。我们的界定显示了最小化源域误差和边际分布不匹配的不足,因为由于可能的诱导标记功能不匹配可能增加,因此由于可能的增加而减少目标域误差。通过同一UDA方法成功,失败的简单分布进一步说明了这种不足,并且可以成功或失败,并且可以使用相同的机会。从此激励,我们提出了新的数据中毒攻击,以欺骗UDA方法进入产生大目标域错误的学习陈述。我们使用基准数据集评估这些攻击对流行的UDA方法的影响,他们以前已经证明是成功的。我们的结果表明,中毒可以显着降低目标域精度,在某些情况下将其降至近0%,在源域中添加了10%中毒数据。这些UDA方法的失败在保证与我们下限符合的跨域泛化时,他们的局限性阐述了它们的局限性。因此,评估诸如数据中毒等对逆势设置中的UDA方法提供了更好的稳健性对UDA不利的数据分布。
translated by 谷歌翻译
Recent work reported the label alignment property in a supervised learning setting: the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix. Inspired by this observation, we derive a regularization method for unsupervised domain adaptation. Instead of regularizing representation learning as done by popular domain adaptation methods, we regularize the classifier so that the target domain predictions can to some extent ``align" with the top singular vectors of the unsupervised data matrix from the target domain. In a linear regression setting, we theoretically justify the label alignment property and characterize the optimality of the solution of our regularization by bounding its distance to the optimal solution. We conduct experiments to show that our method can work well on the label shift problems, where classic domain adaptation methods are known to fail. We also report mild improvement over domain adaptation baselines on a set of commonly seen MNIST-USPS domain adaptation tasks and on cross-lingual sentiment analysis tasks.
translated by 谷歌翻译
学习域不变的表示已成为域适应/概括的最受欢迎的方法之一。在本文中,我们表明不变的表示可能不足以保证良好的概括,在考虑标签函数转移的情况下。受到这一点的启发,我们首先在经验风险上获得了新的概括上限,该概括风险明确考虑了标签函数移动。然后,我们提出了特定领域的风险最小化(DRM),该风险最小化(DRM)可以分别对不同域的分布移动进行建模,并为目标域选择最合适的域。对四个流行的域概括数据集(CMNIST,PACS,VLCS和域)进行了广泛的实验,证明了所提出的DRM对域泛化的有效性,具有以下优点:1)它的表现明显超过了竞争性盆地的表现; 2)与香草经验风险最小化(ERM)相比,所有训练领域都可以在所有训练领域中具有可比性或优越的精度; 3)在培训期间,它仍然非常简单和高效,4)与不变的学习方法是互补的。
translated by 谷歌翻译
转移学习或域适应性与机器学习问题有关,在这些问题中,培训和测试数据可能来自可能不同的概率分布。在这项工作中,我们在Russo和Xu发起的一系列工作之后,就通用错误和转移学习算法的过量风险进行了信息理论分析。我们的结果也许表明,也许正如预期的那样,kullback-leibler(kl)Divergence $ d(\ mu || \ mu')$在$ \ mu $和$ \ mu'$表示分布的特征中起着重要作用。培训数据和测试测试。具体而言,我们为经验风险最小化(ERM)算法提供了概括误差上限,其中两个分布的数据在训练阶段都可用。我们进一步将分析应用于近似的ERM方法,例如Gibbs算法和随机梯度下降方法。然后,我们概括了与$ \ phi $ -Divergence和Wasserstein距离绑定的共同信息。这些概括导致更紧密的范围,并且在$ \ mu $相对于$ \ mu' $的情况下,可以处理案例。此外,我们应用了一套新的技术来获得替代的上限,该界限为某些学习问题提供了快速(最佳)的学习率。最后,受到派生界限的启发,我们提出了Infoboost算法,其中根据信息测量方法对源和目标数据的重要性权重进行了调整。经验结果表明了所提出的算法的有效性。
translated by 谷歌翻译
对抗性学习策略在处理单源域适应(DA)问题时表现出显着的性能,并且最近已应用于多源DA(MDA)问题。虽然大多数现有的MDA策略依赖于多个域歧视员设置,但其对潜伏空间表示的影响已经不知识。在这里,我们采用了一种信息 - 理论方法来识别和解决MDA上多个域鉴别器的潜在不利影响:域歧视信息的解体,有限的计算可扩展性以及培训期间损失梯度的大方差。我们在信息正规化的背景下通过情况进行对抗性DA来检查上述问题。这还提供了使用单一和统一域鉴别器的理论正当理由。基于这个想法,我们实施了一种名为多源信息正规化适应网络(MIAN)的新型神经结构。大规模实验表明,尽管其结构简洁,可靠,可显着优于其他最先进的方法。
translated by 谷歌翻译
虽然在许多域内生成并提供了大量的未标记数据,但对视觉数据的自动理解的需求高于以往任何时候。大多数现有机器学习模型通常依赖于大量标记的训练数据来实现高性能。不幸的是,在现实世界的应用中,不能满足这种要求。标签的数量有限,手动注释数据昂贵且耗时。通常需要将知识从现有标记域传输到新域。但是,模型性能因域之间的差异(域移位或数据集偏差)而劣化。为了克服注释的负担,域适应(DA)旨在在将知识从一个域转移到另一个类似但不同的域中时减轻域移位问题。无监督的DA(UDA)处理标记的源域和未标记的目标域。 UDA的主要目标是减少标记的源数据和未标记的目标数据之间的域差异,并在培训期间在两个域中学习域不变的表示。在本文中,我们首先定义UDA问题。其次,我们从传统方法和基于深度学习的方法中概述了不同类别的UDA的最先进的方法。最后,我们收集常用的基准数据集和UDA最先进方法的报告结果对视觉识别问题。
translated by 谷歌翻译
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation (M 3 SDA), which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. Third, we provide new theoretical insights specifically for moment matching approaches in both single and multiple source domain adaptation. Extensive experiments are conducted to demonstrate the power of our new dataset in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model. Dataset and Code are available at http://ai.bu.edu/M3SDA/
translated by 谷歌翻译
分发概括是将模型从实验室转移到现实世界时的关键挑战之一。现有努力主要侧重于源和目标域之间建立不变的功能。基于不变的功能,源域上的高性能分类可以在目标域上同样良好。换句话说,不变的功能是\ emph {transcorable}。然而,在实践中,没有完全可转换的功能,并且一些算法似乎学习比其他算法更学习“更可转移”的特征。我们如何理解和量化此类\ EMPH {可转录性}?在本文中,我们正式定义了一种可以量化和计算域泛化的可转换性。我们指出了与域之间的常见差异措施的差异和连接,例如总变化和Wassersein距离。然后,我们证明我们可以使用足够的样本估计我们的可转换性,并根据我们的可转移提供目标误差的新上限。经验上,我们评估现有算法学习的特征嵌入的可转换性,以获得域泛化。令人惊讶的是,我们发现许多算法并不完全学习可转让的功能,尽管很少有人仍然可以生存。鉴于此,我们提出了一种用于学习可转移功能的新算法,并在各种基准数据集中测试,包括RotationMnist,PACS,Office和Wilds-FMOW。实验结果表明,该算法在许多最先进的算法上实现了一致的改进,证实了我们的理论发现。
translated by 谷歌翻译
多类神经网络是现代无监督的领域适应性中的常见工具,但是在适应性文献中缺乏针对其非均匀样品复杂性的适当理论描述。为了填补这一空白,我们为多类学习者提出了第一个Pac-Bayesian适应范围。我们还提出了我们考虑的多类分布差异的第一个近似技术,从而促进了界限的实际使用。对于依赖Gibbs预测因子的分歧,我们提出了其他PAC-湾适应界限,以消除对蒙特卡洛效率低下的需求。从经验上讲,我们测试了我们提出的近似技术的功效以及一些新型的设计概念,我们在范围中包括。最后,我们应用界限来分析使用神经网络的常见适应算法。
translated by 谷歌翻译
机器学习(ML)鲁棒性和域的概括从根本上相关:它们基本上涉及对抗和自然设置下的数据分布变化。一方面,最近的研究表明,更健壮的(受对抗训练)模型更为普遍。另一方面,缺乏对其基本联系的理论理解。在本文中,我们探讨了考虑到不同因素(例如规范正规化和数据增强)(DA)等不同因素的正则化和域转移性之间的关系。我们提出了一个一般的理论框架,证明涉及模型函数类正则化的因素是相对域可传递性的足够条件。我们的分析意味着``鲁棒性''既不必需,也不足以使其可转移性;而正规化是理解域可转移性的更基本的观点。然后,我们讨论流行的DA协议(包括对抗性培训),并显示何时可以将其视为功能在某些条件下进行类正则化并因此改善了概括。我们进行了广泛的实验以验证我们的理论发现,并显示了几个反例,其中鲁棒性和概括在不同的数据集上呈负相关。
translated by 谷歌翻译
伪标签的使用占上处,以解决无监督的域自适应(UDA)重新识别(RE-ID),具有最佳性能。事实上,这家族的方法已经上升到几个有效的UDA重新ID特定框架。在这些作品中,改善伪标签UDA重新ID性能的研究方向多样化,主要基于直觉和实验:炼制伪标签,减少伪标签中的错误的影响......它可能很难推断出来它们是一般的良好做法,可以以任何伪标记方法实施,以始终如一地提高其性能。为了解决这一关键问题,提出了一个关于伪标签UDA RE-ID的新的理论视图。这些贡献是三倍:(i)伪标签UDA重新ID的新理论框架,通过UDA重新ID性能的新一般学习上限,正式化。 (ii)伪标签的一般良好做法,直接推导出拟议的理论框架的解释,以改善目标重新ID表现。 (iii)关于具有挑战性的人和车辆交叉数据集重新ID任务的广泛实验,对各种最先进的方法和各种建议的良好实践实现显示了一致的性能改进。
translated by 谷歌翻译