神经体系结构搜索(NAS)的主要挑战之一是有效地对体系结构的性能进行排名。绩效排名者的主流评估使用排名相关性(例如,肯德尔的tau),这对整个空间都同样关注。但是,NAS的优化目标是识别顶级体系结构,同时对搜索空间中其他体系结构的关注更少。在本文中,我们从经验和理论上都表明,标准化的累积累积增益(NDCG)对于排名者来说是一个更好的指标。随后,我们提出了一种新算法Acenas,该算法直接通过Lambdarank优化NDCG。它还利用体重共享NAS产生的弱标签来预先培训排名,以便进一步降低搜索成本。对12个NAS基准和大规模搜索空间进行的广泛实验表明,我们的方法始终超过SOTA NAS方法,精度提高了3.67%,搜索成本降低了8倍。
translated by 谷歌翻译
神经结构搜索(NAS)经常列车并评估大量架构。最近的基于预测的NAS方法尝试通过两个关键步骤来缓解这些重的计算成本:采样一些架构性能对并拟合代理精度预测器。然而,由于难以拟合庞大的搜索空间,所以这些预测变量远非准确地定位顶级架构。本文反映了一个简单而重要的问题:如果我们的最终目标是找到最好的建筑,我们真的需要融洽整个空间吗?我们提出了一种使用一个强预测器来拟合整个建筑空间的范式转变,以通过一组较弱的预测器逐渐地拟合朝向高性能子空间的搜索路径。作为弱预测因子的关键属性,它们的采样更好的架构的概率不断增加。因此,我们只示出了一些由以前学识到的预测器引导的少数好的架构,并估计一个新的更好的弱预测因素。这种令人尴尬的骨骼框架被称为缺点,产生粗略迭代,逐渐改进采样空间的排名。广泛的实验表明,在NAS-Bench-101和NAS-Bench-201上找到顶部性能架构的样本较少的缺点。与最先进的(SOTA)基于预测的NAS方法相比,缺点始终具有显着的边距,例如,需要至少7.5倍的样品来查找在NAS-Bench-101上的全局最优。缺点也可以吸收他们的想法,以提高性能。此外,缺点袭击了Imagenet MobileNet搜索空间中的81.3%的新SOTA结果。代码可在https://github.com/vita-group/weaknas获得。
translated by 谷歌翻译
神经体系结构搜索(NAS)是自动化有效图像处理DNN设计的强大工具。该排名已被倡导为NAS设计有效的性能预测指标。先前的对比方法通过比较架构对并预测其相对性能来解决排名问题。但是,它仅关注两个相关建筑之间的排名,而忽略了搜索空间的整体质量分布,这可能会遇到概括性问题。提出了一个预测因子,即专注于特定体系结构的全球质量层的神经体系结构排名,以解决由当地观点引起的此类问题。 NAR在全球范围内探索搜索空间的质量层,并根据其全球排名将每个人分类为他们所属的层。因此,预测变量获得了搜索空间的性能分布的知识,这有助于更轻松地将其排名能力推广到数据集。同时,全球质量分布通过根据质量层的统计数据直接对候选者进行采样,从而促进了搜索阶段,而质量层的统计数据没有培训搜索算法,例如增强型学习(RL)或进化算法(EA),因此简化了NAS管道并保存计算开销。拟议的NAR比在两个广泛使用的NAS研究数据集上的最先进方法取得了更好的性能。在NAS-Bench-101的庞大搜索空间中,NAR可以轻松地找到具有最高0.01 $ \ unicode {x2030} $ performance的架构。它还可以很好地概括为NAS Bench-201的不同图像数据集,即CIFAR-10,CIFAR-100和Imagenet-16-120,通过识别每个它们的最佳体系结构。
translated by 谷歌翻译
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally. Comprehensive experiments verify that our approach is flexible and effective. It is easy to train and fast to search. It effortlessly supports complex search spaces (e.g., building blocks, channel, mixed-precision quantization) and different search constraints (e.g., FLOPs, latency). It is thus convenient to use for various needs. It achieves start-of-the-art performance on the large dataset ImageNet.Equal contribution. This work is done when Haoyuan Mu and Zechun Liu are interns at MEGVII Technology.
translated by 谷歌翻译
Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance predictors which are limited to modeling architectures in a predefined design space involving specific sets of operators and connection rules, and cannot generalize to unseen architectures, or resort to zero-cost proxies which are not always accurate. In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble. Specifically, GENNAPE represents a given neural network as a Computation Graph (CG) of atomic operations which can model an arbitrary architecture. It first learns a graph encoder via Contrastive Learning to encourage network separation by topological features, and then trains multiple predictor heads, which are soft-aggregated according to the fuzzy membership of a neural network. Experiments show that GENNAPE pretrained on NAS-Bench-101 can achieve superior transferability to 5 different public neural network benchmarks, including NAS-Bench-201, NAS-Bench-301, MobileNet and ResNet families under no or minimum fine-tuning. We further introduce 3 challenging newly labelled neural network benchmarks: HiAML, Inception and Two-Path, which can concentrate in narrow accuracy ranges. Extensive experiments show that GENNAPE can correctly discern high-performance architectures in these families. Finally, when paired with a search algorithm, GENNAPE can find architectures that improve accuracy while reducing FLOPs on three families.
translated by 谷歌翻译
Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the precomputed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.
translated by 谷歌翻译
神经体系结构搜索(NAS)的关键挑战是迅速推断了广泛的网络的预测性能,以发现统计准确和计算高效的网络。我们将此任务称为模型性能推断(MPI)。当前的有效MPI实践是基于梯度的方法,可利用网络初始化的梯度来推断其性能。但是,现有的基于梯度的方法仅依赖启发式指标,并且缺乏必要的理论基础来巩固其设计。我们提出了GradSign,一种准确,简单且灵活的指标,用于使用理论见解的模型性能推断。 GradSign背后的关键思想是一个数量{\ psi},以分析单个训练样本粒度下不同网络的优化格局。从理论上讲,我们表明,在合理的假设下,网络的培训和真实的人口损失都由{\ psi}在相称的上限。此外,我们设计了GradSign,使用在随机初始化状态下评估的网络梯度对{\ psi}进行精确而简单的近似。对三个培训数据集的七个NAS基准进行评估表明,毕业生对现实世界的网络很好地推广,并且始终优于Spearman的{\ rho}和Kendall's Tau评估的基于最新的基于梯度的MPI。此外,我们将GradSign集成到四种现有的NAS算法中,并表明,通过将最佳发现网络的准确性提高高达0.3%,1.1%和1.0%,这三个现实世界任务的精确度提高了毕业生辅助的NAS算法的表现优于其香草。 。
translated by 谷歌翻译
深度学习技术在各种任务中都表现出了出色的有效性,并且深度学习具有推进多种应用程序(包括在边缘计算中)的潜力,其中将深层模型部署在边缘设备上,以实现即时的数据处理和响应。一个关键的挑战是,虽然深层模型的应用通常会产生大量的内存和计算成本,但Edge设备通常只提供非常有限的存储和计算功能,这些功能可能会在各个设备之间差异很大。这些特征使得难以构建深度学习解决方案,以释放边缘设备的潜力,同时遵守其约束。应对这一挑战的一种有希望的方法是自动化有效的深度学习模型的设计,这些模型轻巧,仅需少量存储,并且仅产生低计算开销。该调查提供了针对边缘计算的深度学习模型设计自动化技术的全面覆盖。它提供了关键指标的概述和比较,这些指标通常用于量化模型在有效性,轻度和计算成本方面的水平。然后,该调查涵盖了深层设计自动化技术的三类最新技术:自动化神经体系结构搜索,自动化模型压缩以及联合自动化设计和压缩。最后,调查涵盖了未来研究的开放问题和方向。
translated by 谷歌翻译
这项工作调查了神经架构搜索中的批量标准化(NAS)。具体来说,Frankle等人。发现培训Batchnorm只能实现非竞争性能。此外,陈等人。声称培训Batchnorm只能加快10次单次NAS超网关的培训。批判性地,没有努力理解1)为什么训练Batchnorm只能找到具有减少的超空网训练时间的表演井架构,而且2)列车-BN的超网和标准列车超空网之间有什么区别。我们首先显示列车-BN网络融合到神经切线内核制度,从理论上获得与所有参数的所有参数相同的训练动态。我们的证据支持索赔仅在超培训时间上训练Batchnorm。然后,我们经验披露了培训-BN的超标网络在其他运营商的卷曲中提供了优势,导致架构之间的不公平竞争。这是因为只有卷积运算符被附加到Batchnorm。通过实验,我们表明这种不公平性使得搜索算法容易选择具有卷积的模型。为了解决这个问题,我们通过在每个操作员上放置批处理层来引入搜索空间的公平性。然而,我们观察到Chen等人的性能预测因子。在新的搜索空间上不可应用。为此,我们提出了一种新颖的综合性能指标,从三个视角评估网络:源自Batchnorm的理论属性的表达性,培训和不确定性。我们展示了我们对多NAS基准的方法(NAS-BENCH101,NAS-BENCH-201)和搜索空间(飞镖搜索空间和MOBILENET搜索空间)的有效性。
translated by 谷歌翻译
神经体系结构搜索(NAS)最近在深度学习社区中变得越来越流行,主要是因为它可以提供一个机会,使感兴趣的用户没有丰富的专业知识,从而从深度神经网络(DNNS)的成功中受益。但是,NAS仍然很费力且耗时,因为在NAS的搜索过程中需要进行大量的性能估计,并且训练DNNS在计算上是密集的。为了解决NAS的主要局限性,提高NAS的效率对于NAS的设计至关重要。本文以简要介绍了NAS的一般框架。然后,系统地讨论了根据代理指标评估网络候选者的方法。接下来是对替代辅助NAS的描述,该NAS分为三个不同类别,即NAS的贝叶斯优化,NAS的替代辅助进化算法和NAS的MOP。最后,讨论了剩余的挑战和开放研究问题,并在这个新兴领域提出了有希望的研究主题。
translated by 谷歌翻译
许多现有的神经结构搜索(NAS)解决方案依赖于架构评估的下游培训,这需要巨大的计算。考虑到这些计算带来了大量碳足迹,本文旨在探索绿色(即环保)NAS解决方案,可以在不培训的情况下评估架构。直观地,由架构本身引起的梯度,直接决定收敛和泛化结果。它激励我们提出梯度内核假设:梯度可以用作下游训练的粗粒粒度,以评估随机初始化网络。为了支持假设,我们进行理论分析,找到一个实用的梯度内核,与培训损失和验证性能有良好的相关性。根据这一假设,我们提出了一种新的基于内核的架构搜索方法knas。实验表明,KNA可实现比图像分类任务的“火车-TER-TEST”范式更快地实现竞争力。此外,极低的搜索成本使其具有广泛的应用。搜索网络还优于两个文本分类任务的强大基线Roberta-Light。代码可用于\ url {https://github.com/jingjing-nlp/knas}。
translated by 谷歌翻译
功能提取器在文本识别(TR)中起着至关重要的作用,但是由于昂贵的手动调整,自定义其体系结构的探索相对较少。在这项工作中,受神经体系结构搜索(NAS)的成功启发,我们建议搜索合适的功能提取器。我们通过探索具有良好功能提取器的原理来设计特定于域的搜索空间。该空间包括用于空间模型的3D结构空间和顺序模型的基于转换的空间。由于该空间是巨大且结构复杂的,因此无法应用现有的NAS算法。我们提出了一种两阶段算法,以有效地在空间中进行搜索。在第一阶段,我们将空间切成几个块,并借助辅助头逐步训练每个块。我们将延迟约束引入第二阶段,并通过自然梯度下降从受过训练的超级网络搜索子网络。在实验中,进行了一系列消融研究,以更好地了解设计的空间,搜索算法和搜索架构。我们还将所提出的方法与手写和场景TR任务上的各种最新方法进行了比较。广泛的结果表明,我们的方法可以以较小的延迟获得更好的识别性能。
translated by 谷歌翻译
Neural architectures can be naturally viewed as computational graphs. Motivated by this perspective, we, in this paper, study neural architecture search (NAS) through the lens of learning random graph models. In contrast to existing NAS methods which largely focus on searching for a single best architecture, i.e, point estimation, we propose GraphPNAS a deep graph generative model that learns a distribution of well-performing architectures. Relying on graph neural networks (GNNs), our GraphPNAS can better capture topologies of good neural architectures and relations between operators therein. Moreover, our graph generator leads to a learnable probabilistic search method that is more flexible and efficient than the commonly used RNN generator and random search methods. Finally, we learn our generator via an efficient reinforcement learning formulation for NAS. To assess the effectiveness of our GraphPNAS, we conduct extensive experiments on three search spaces, including the challenging RandWire on TinyImageNet, ENAS on CIFAR10, and NAS-Bench-101/201. The complexity of RandWire is significantly larger than other search spaces in the literature. We show that our proposed graph generator consistently outperforms RNN-based one and achieves better or comparable performances than state-of-the-art NAS methods.
translated by 谷歌翻译
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. Recent NAS works start to explore indicators that can predict a network's performance without training. However, they either leveraged limited properties of deep networks, or the benefits of their training-free indicators are not applied to more extensive search methods. By rigorous correlation analysis, we present a unified framework to understand and accelerate NAS, by disentangling "TEG" characteristics of searched networks - Trainability, Expressivity, Generalization - all assessed in a training-free manner. The TEG indicators could be scaled up and integrated with various NAS search methods, including both supernet and single-path approaches. Extensive studies validate the effective and efficient guidance from our TEG-NAS framework, leading to both improved search accuracy and over 56% reduction in search time cost. Moreover, we visualize search trajectories on three landscapes of "TEG" characteristics, observing that while a good local minimum is easier to find on NAS-Bench-201 given its simple topology, balancing "TEG" characteristics is much harder on the DARTS search space due to its complex landscape geometry. Our code is available at https://github.com/VITA-Group/TEGNAS.
translated by 谷歌翻译
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, we evaluate both random search with early-stopping and a novel random search with weight-sharing algorithm on two standard NAS benchmarks-PTB and CIFAR-10. Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS [41], a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Finally, we explore the existing reproducibility issues of published NAS results. We note the lack of source material needed to exactly reproduce these results, and further discuss the robustness of published results given the various sources of variability in NAS experimental setups. Relatedly, we provide all information (code, random seeds, documentation) needed to exactly reproduce our results, and report our random search with weight-sharing results for each benchmark on multiple runs.
translated by 谷歌翻译
体重共享是一种流行的方法,可以通过重复以前训练的儿童模型的共享操作员的权重来降低神经体系结构搜索(NAS)的成本。但是,由于重量共享引起的不同儿童模型之间的干扰,这些儿童模型的估计准确性和地面真实准确性之间的等级相关性很低。在本文中,我们通过对不同的儿童模型进行采样并计算共享操作员的梯度相似性来研究干扰问题,并观察:1)两个儿童模型之间对共享操作员的干扰与不同操作员的数量正相关; 2)当共享操作员的输入和输出更相似时,干扰较小。受这两个观察结果的启发,我们提出了两种减轻干扰的方法:1)魔术-T:而不是随机采样儿童模型以进行优化,而是通过在相邻优化步骤之间修改一个操作员来最大程度地减少对干扰的干扰,从而提出了一种逐步修改方案。共享操作员; 2)Magic-A:强迫所有儿童模型的操作员的输入和输出与减少干扰相似。在BERT搜索空间上进行的实验证明,通过我们提出的每种方法来缓解干扰可以改善Super-PET的秩相关性,并结合两种方法可以取得更好的结果。我们发现的体系结构优于Roberta $ _ {\ rm base} $ 1.1和0.6分,而Electra $ _ {\ rm base} $在DEV和测试集的粘合基准的$ 1.6和1.1分。关于BERT压缩,阅读理解和成像网任务的广泛结果证明了我们提出的方法的有效性和普遍性。
translated by 谷歌翻译
现代神经结构搜索方法对几个学科进行了多次破坏最先进的结果。超级网络,许多这样的方法的中心组件,可以快速估计搜索空间中的任何架构的准确性或损失统计数据。它们包含所有候选架构的网络权重,因此可以通过应用各个操作来近似特定的。但是,这种设计忽略了连续操作之间的潜在依赖关系。我们将超级网络扩展到有条件的权重,这些重量取决于选择的组合并分析它们的效果。NAS - 台凳201和基于NAS - 台型宏的搜索空间的实验显示了架构选择的改进,并且资源开销几乎可以忽略不计,以便顺序网络设计。
translated by 谷歌翻译
卷积神经网络(CNNS)用于许多现实世界应用,例如基于视觉的自主驾驶和视频内容分析。要在各种目标设备上运行CNN推断,硬件感知神经结构搜索(NAS)至关重要。有效的硬件感知NAS的关键要求是对推理延迟的快速评估,以便对不同的架构进行排名。在构建每个目标设备的延迟预测器的同时,在本领域中通常使用,这是一个非常耗时的过程,在极定的设备存在下缺乏可扩展性。在这项工作中,我们通过利用延迟单调性来解决可扩展性挑战 - 不同设备上的架构延迟排名通常相关。当存在强烈的延迟单调性时,我们可以重复使用在新目标设备上搜索一个代理设备的架构,而不会丢失最佳状态。在没有强烈的延迟单调性的情况下,我们提出了一种有效的代理适应技术,以显着提高延迟单调性。最后,我们验证了我们的方法,并在多个主流搜索空间上使用不同平台的设备进行实验,包括MobileNet-V2,MobileNet-V3,NAS-Bench-201,Proxylessnas和FBNet。我们的结果突出显示,通过仅使用一个代理设备,我们可以找到几乎与现有的每个设备NAS相同的帕累托最优架构,同时避免为每个设备构建延迟预测器的禁止成本。 github:https://github.com/ren-research/oneproxy.
translated by 谷歌翻译
具有密集乘法的神经网络(NNS)(例如,卷积和变形金刚)具有饥饿的能力,阻碍了它们更广泛的部署到资源受限的设备中。因此,遵循节能硬件实施的共同实践的无乘法网络,以更有效的运算符(例如,位移位和加法)参数化NN,并引起了人们的关注。但是,从实现的准确性方面,无乘法网络的表现不足。为此,这项工作倡导混合NN,包括强大但昂贵的乘法和有效而强大的运营商来嫁给两全其美的运营商,并提出了ShiftAddnas,它们可以自动寻找更准确,更有效的NN。我们的ShiftAddnas突出了两个推动者。具体而言,它集成了(1)第一个混合搜索空间,该空间同时结合了基于乘法的和无乘法的运算符,以促进精确和有效的混合NNS的开发; (2)一种新型的重量共享策略,可以在遵循异质分布的不同操作员之间有效分享(例如,用于卷积的高斯与添加操作员的拉普拉斯人),并同时导致超级降低的超网尺寸和更好的搜索网络。对各种模型,数据集和任务的广泛实验和消融研究始终如一地验证了ShiftAddnas的功效,例如,与最先进的NN相比,获得的精度高达 +4.7%,或者+4.9更好的BLEU得分,而BLEU得分更好最多可提供93%或69%的能源和延迟节省。可以在https://github.com/rice-eic/shiftaddnas上获得代码和预估计的模型。
translated by 谷歌翻译
The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the industry. Neural Architecture Search (NAS) exploits deep learning techniques to autonomously produce neural network architectures whose results rival the state-of-the-art models hand-crafted by AI experts. However, this approach requires significant computational resources and hardware investments, making it less appealing for real-usage applications. This article presents the third version of Pareto-Optimal Progressive Neural Architecture Search (POPNASv3), a new sequential model-based optimization NAS algorithm targeting different hardware environments and multiple classification tasks. Our method is able to find competitive architectures within large search spaces, while keeping a flexible structure and data processing pipeline to adapt to different tasks. The algorithm employs Pareto optimality to reduce the number of architectures sampled during the search, drastically improving the time efficiency without loss in accuracy. The experiments performed on images and time series classification datasets provide evidence that POPNASv3 can explore a large set of assorted operators and converge to optimal architectures suited for the type of data provided under different scenarios.
translated by 谷歌翻译