In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, we introduce a new metric measuring how quickly a learner acquires a new skill. Third, we propose an improved version of GEM (Lopez-Paz & Ranzato, 2017), dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC and other regularizationbased methods. Finally, we show that all algorithms including A-GEM can learn even more quickly if they are provided with task descriptors specifying the classification tasks under consideration. Our experiments on several standard lifelong learning benchmarks demonstrate that A-GEM has the best trade-off between accuracy and efficiency. 1
translated by 谷歌翻译
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model observes, once and one by one, examples concerning a sequence of tasks. First, we propose a set of metrics to evaluate models learning over a continuum of data. These metrics characterize models not only by their test accuracy, but also in terms of their ability to transfer knowledge across tasks. Second, we propose a model for continual learning, called Gradient Episodic Memory (GEM) that alleviates forgetting, while allowing beneficial transfer of knowledge to previous tasks. Our experiments on variants of the MNIST and CIFAR-100 datasets demonstrate the strong performance of GEM when compared to the state-of-the-art.
translated by 谷歌翻译
当代理在终身学习设置中遇到连续的新任务流时,它利用了从早期任务中获得的知识来帮助更好地学习新任务。在这种情况下,确定有效的知识表示成为一个具有挑战性的问题。大多数研究工作都建议将过去任务中的一部分示例存储在重播缓冲区中,将一组参数集成给每个任务,或通过引入正则化项来对参数进行过多的更新。尽管现有方法采用了一般任务无关的随机梯度下降更新规则,但我们提出了一个任务吸引的优化器,可根据任务之间的相关性调整学习率。我们通过累积针对每个任务的梯度来利用参数在更新过程中采取的方向。这些基于任务的累积梯度充当了在整个流中维护和更新的知识库。我们从经验上表明,我们提出的自适应学习率不仅说明了灾难性的遗忘,而且还允许积极的向后转移。我们还表明,在具有大量任务的复杂数据集中,我们的方法比终身学习中的几种最先进的方法更好。
translated by 谷歌翻译
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. 1 We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.
translated by 谷歌翻译
Incremental learning (IL) has received a lot of attention recently, however, the literature lacks a precise problem definition, proper evaluation settings, and metrics tailored specifically for the IL problem. One of the main objectives of this work is to fill these gaps so as to provide a common ground for better understanding of IL. The main challenge for an IL algorithm is to update the classifier whilst preserving existing knowledge. We observe that, in addition to forgetting, a known issue while preserving knowledge, IL also suffers from a problem we call intransigence, inability of a model to update its knowledge. We introduce two metrics to quantify forgetting and intransigence that allow us to understand, analyse, and gain better insights into the behaviour of IL algorithms. We present RWalk, a generalization of EWC++ (our efficient version of EWC [7]) and Path Integral [26] with a theoretically grounded KL-divergence based perspective. We provide a thorough analysis of various IL algorithms on MNIST and CIFAR-100 datasets. In these experiments, RWalk obtains superior results in terms of accuracy, and also provides a better trade-off between forgetting and intransigence.
translated by 谷歌翻译
在许多实际应用中,机器学习数据随着时间的流逝依次到达大块。然后,从业者必须决定如何分配其计算预算,以便在任何时间点获得最佳性能。凸优化的在线学习理论表明,最佳策略是在到达时立即使用数据。但是,这可能不是使用深度非线性网络时的最佳策略,尤其是当这些网络对每个数据进行多个数据进行多次通过时,呈现整体分布而非i.i.d ..在本文中,我们在最简单的情况下将此学习环境正式化。每个数据块都是从相同的基础分布中得出的,并首次尝试从经验回答以下问题:学习者在培训新来的块之前应该等待多长时间?学习者应该采用哪些架构?随着观察到更多的数据,学习者是否应该随着时间的推移增加能力吗?我们使用经典计算机视觉基准测试的卷积神经网络以及在大规模语言建模任务中训练的大型变压器模型进行探讨。代码可在\ url {www.github.com/facebookresearch/alma}中获得。
translated by 谷歌翻译
我们探索无任务持续学习(CL),其中培训模型以避免在没有明确的任务边界或身份的情况下造成灾难性的遗忘。在无任务CL上的许多努力中,一个值得注意的方法是基于内存的,存储和重放训练示例的子集。然而,由于CL模型不断更新,所以存储的示例的效用可以随时间缩短。这里,我们提出基于梯度的存储器编辑(GMED),该框架是通过梯度更新在连续输入空间中编辑存储的示例的框架,以便为重放创建更多的“具有挑战性”示例。 GMED编辑的例子仍然类似于其未编辑的形式,但可以在即将到来的模型更新中产生增加的损失,从而使未来的重播在克服灾难性遗忘方面更有效。通过施工,GMED可以与其他基于内存的CL算法一起无缝应用,以进一步改进。实验验证了GMED的有效性,以及我们最好的方法显着优于基线和以前的五个数据集中的最先进。可以在https://github.com/ink-usc/gmed找到代码。
translated by 谷歌翻译
大多数元学习方法都假设存在于可用于基本知识的情节元学习的一组非常大的标记数据。这与更现实的持续学习范例形成对比,其中数据以包含不相交类的任务的形式逐步到达。在本文中,我们考虑了这个增量元学习(IML)的这个问题,其中类在离散任务中逐步呈现。我们提出了一种方法,我们调用了IML,我们称之为eCISODIC重播蒸馏(ERD),该方法将来自当前任务的类混合到当前任务中,当研究剧集时,来自先前任务的类别示例。然后将这些剧集用于知识蒸馏以最大限度地减少灾难性的遗忘。四个数据集的实验表明ERD超越了最先进的。特别是,在一次挑战的单次次数较挑战,长任务序列增量元学习场景中,我们将IML和联合训练与当前状态的3.5%/ 10.1%/ 13.4%之间的差距降低我们在Diered-ImageNet / Mini-ImageNet / CIFAR100上分别为2.6%/ 2.9%/ 5.0%。
translated by 谷歌翻译
持续学习研究的主要重点领域是通过设计新算法对分布变化更强大的新算法来减轻神经网络中的“灾难性遗忘”问题。尽管持续学习文献的最新进展令人鼓舞,但我们对神经网络的特性有助于灾难性遗忘的理解仍然有限。为了解决这个问题,我们不关注持续的学习算法,而是在这项工作中专注于模型本身,并研究神经网络体系结构对灾难性遗忘的“宽度”的影响,并表明宽度在遗忘遗产方面具有出人意料的显着影响。为了解释这种效果,我们从各个角度研究网络的学习动力学,例如梯度正交性,稀疏性和懒惰的培训制度。我们提供了与不同架构和持续学习基准之间的经验结果一致的潜在解释。
translated by 谷歌翻译
持续学习旨在快速,不断地从一系列任务中学习当前的任务。与其他类型的方法相比,基于经验重播的方法表现出了极大的优势来克服灾难性的遗忘。该方法的一个常见局限性是上一个任务和当前任务之间的数据不平衡,这将进一步加剧遗忘。此外,如何在这种情况下有效解决稳定性困境也是一个紧迫的问题。在本文中,我们通过提出一个通过多尺度知识蒸馏和数据扩展(MMKDDA)提出一个名为Meta学习更新的新框架来克服这些挑战。具体而言,我们应用多尺度知识蒸馏来掌握不同特征级别的远程和短期空间关系的演变,以减轻数据不平衡问题。此外,我们的方法在在线持续训练程序中混合了来自情节记忆和当前任务的样品,从而减轻了由于概率分布的变化而减轻了侧面影响。此外,我们通过元学习更新来优化我们的模型,该更新诉诸于前面所看到的任务数量,这有助于保持稳定性和可塑性之间的更好平衡。最后,我们对四个基准数据集的实验评估显示了提出的MMKDDA框架对其他流行基线的有效性,并且还进行了消融研究,以进一步分析每个组件在我们的框架中的作用。
translated by 谷歌翻译
根据互补学习系统(CLS)理论〜\ cite {mcclelland1995there}在神经科学中,人类通过两个补充系统有效\ emph {持续学习}:一种快速学习系统,以海马为中心,用于海马,以快速学习细节,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验的快速学习, ;以及位于新皮层中的缓慢学习系统,以逐步获取有关环境的结构化知识。在该理论的激励下,我们提出\ emph {dualnets}(对于双网络),这是一个一般的持续学习框架,该框架包括一个快速学习系统,用于监督从特定任务和慢速学习系统中的模式分离代表学习,用于表示任务的慢学习系统 - 不可知论的一般代表通过自我监督学习(SSL)。双网符可以无缝地将两种表示类型纳入整体框架中,以促进在深层神经网络中更好地持续学习。通过广泛的实验,我们在各种持续的学习协议上展示了双网络的有希望的结果,从标准离线,任务感知设置到具有挑战性的在线,无任务的场景。值得注意的是,在Ctrl〜 \ Cite {veniat2020202020202020202020202020202020202020202020202020202020202021- coite {ostapenko2021-continual}的基准中。此外,我们进行了全面的消融研究,以验证双nets功效,鲁棒性和可伸缩性。代码可在\ url {https://github.com/phquang/dualnet}上公开获得。
translated by 谷歌翻译
本文认为,连续学习方法可以通过分割多种模型的学习者的容量来利益。我们使用统计学习理论和实验分析来展示多种任务在单个型号培训时以非琐碎的方式互相交互。特定任务上的泛化误差可以随着协同任务培训,但在竞争任务训练时也可以恶化。该理论激励了我们名为Model动物园的方法,这是从升压文献的启发,增长了小型型号的集合,每个集中都在持续学习的一集中训练。我们展示了模型动物园的准确性提高了各种持续学习基准问题。
translated by 谷歌翻译
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.
translated by 谷歌翻译
模块化是持续学习(CL)的令人信服的解决方案,是相关任务建模的问题。学习和组合模块来解决不同的任务提供了一种抽象来解决CL的主要挑战,包括灾难性的遗忘,向后和向前传输跨任务以及子线性模型的增长。我们引入本地模块组成(LMC),该方法是模块化CL的方法,其中每个模块都提供了局部结构组件,其估计模块与输入的相关性。基于本地相关评分进行动态模块组合。我们展示了对任务身份(IDS)的不可知性来自(本地)结构学习,该结构学习是特定于模块和/或模型特定于以前的作品,使LMC适用于与以前的作品相比的更多CL设置。此外,LMC还跟踪输入分布的统计信息,并在检测到异常样本时添加新模块。在第一组实验中,LMC与最近的持续转移学习基准上的现有方法相比,不需要任务标识。在另一个研究中,我们表明结构学习的局部性允许LMC插入相关但未遵守的任务(OOD),以及在不同任务序列上独立于不同的任务序列培训的模块化网络,而无需任何微调。最后,在寻找LMC的限制,我们在30和100个任务的更具挑战性序列上研究它,展示了本地模块选择在存在大量候选模块时变得更具挑战性。在此设置中,与Oracle基准的基线相比,最佳执行LMC产生的模块更少,但它达到了较低的总体精度。 CodeBase可在https://github.com/oleksost/lmc下找到。
translated by 谷歌翻译
在基于人工神经网络的终身学习系统中,最大的障碍之一是在遇到新信息时无法保留旧知识。这种现象被称为灾难性遗忘。在本文中,我们提出了一种新型的连接主义架构,即顺序的神经编码网络,在从数据点流中学习时忘记了,并且与当今的网络不同,它不会通过流行的错误反向传播来学习。基于预测性处理的神经认知理论,我们的模型以生物学上可行的方式适应了突触,而另一个神经系统学会了指导和控制这种类似皮层的结构,模仿了一些基础神经节的某些任务连续控制功能。在我们的实验中,我们证明了与标准神经模型相比,我们的自组织系统经历的遗忘大大降低,表现优于先前提出的方法,包括基于排练/数据缓冲的方法,包括标准(SplitMnist,SplitMnist,Split Mnist等) 。)和定制基准测试,即使以溪流式的方式进行了训练。我们的工作提供了证据表明,在实际神经元系统中模仿机制,例如本地学习,横向竞争,可以产生新的方向和可能性,以应对终身机器学习的巨大挑战。
translated by 谷歌翻译
A growing body of research in continual learning focuses on the catastrophic forgetting problem. While many attempts have been made to alleviate this problem, the majority of the methods assume a single model in the continual learning setup. In this work, we question this assumption and show that employing ensemble models can be a simple yet effective method to improve continual performance. However, ensembles' training and inference costs can increase significantly as the number of models grows. Motivated by this limitation, we study different ensemble models to understand their benefits and drawbacks in continual learning scenarios. Finally, to overcome the high compute cost of ensembles, we leverage recent advances in neural network subspace to propose a computationally cheap algorithm with similar runtime to a single model yet enjoying the performance benefits of ensembles.
translated by 谷歌翻译
增量任务学习(ITL)是一个持续学习的类别,试图培训单个网络以进行多个任务(一个接一个),其中每个任务的培训数据仅在培训该任务期间可用。当神经网络接受较新的任务培训时,往往会忘记旧任务。该特性通常被称为灾难性遗忘。为了解决此问题,ITL方法使用情节内存,参数正则化,掩盖和修剪或可扩展的网络结构。在本文中,我们提出了一个基于低级别分解的新的增量任务学习框架。特别是,我们表示每一层的网络权重作为几个等级1矩阵的线性组合。为了更新新任务的网络,我们学习一个排名1(或低级别)矩阵,并将其添加到每一层的权重。我们还引入了一个其他选择器向量,该向量将不同的权重分配给对先前任务的低级矩阵。我们表明,就准确性和遗忘而言,我们的方法的表现比当前的最新方法更好。与基于情节的内存和基于面具的方法相比,我们的方法还提供了更好的内存效率。我们的代码将在https://github.com/csiplab/task-increment-rank-update.git上找到。
translated by 谷歌翻译
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.
translated by 谷歌翻译
人类智慧的主食是以不断的方式获取知识的能力。在Stark对比度下,深网络忘记灾难性,而且为此原因,类增量连续学习促进方法的子字段逐步学习一系列任务,将顺序获得的知识混合成综合预测。这项工作旨在评估和克服我们以前提案黑暗体验重播(Der)的陷阱,这是一种简单有效的方法,将排练和知识蒸馏结合在一起。灵感来自于我们的思想不断重写过去的回忆和对未来的期望,我们赋予了我的能力,即我的能力来修改其重播记忆,以欢迎有关过去数据II的新信息II)为学习尚未公开的课程铺平了道路。我们表明,这些策略的应用导致了显着的改进;实际上,得到的方法 - 被称为扩展-DAR(X-DER) - 优于标准基准(如CiFar-100和MiniimAgeNet)的技术状态,并且这里引入了一个新颖的。为了更好地了解,我们进一步提供了广泛的消融研究,以证实并扩展了我们以前研究的结果(例如,在持续学习设置中知识蒸馏和漂流最小值的价值)。
translated by 谷歌翻译
epiSodic学习是对几枪学习感兴趣的研究人员和从业者的流行练习。它包括在一系列学习问题(或剧集)中组织培训,每个人分为小型训练和验证子集,以模仿评估期间遇到的情况。但这总是必要吗?在本文中,我们调查了在集发作的级别使用非参数方法,例如最近邻居等方法的焦点学习的有用性。对于这些方法,我们不仅展示了广州学习的限制是如何不必要的,而是他们实际上导致利用培训批次的数据低效方式。我们通过匹配和原型网络进行广泛的消融实验,其中两个最流行的方法在集中的级别使用非参数方法。他们的“非焦化”对应物具有很大的更简单,具有较少的近似参数,并在多个镜头分类数据集中提高它们的性能。
translated by 谷歌翻译