在过去的几年中，基于变压器的预训练的语言模型在行业和学术界都取得了惊人的成功。但是，较大的模型尺寸和高运行时间延迟是在实践中应用它们的严重障碍，尤其是在手机和物联网（IoT）设备上。为了压缩该模型，最近有大量文献围绕知识蒸馏（KD）的主题长大。然而，KD在基于变压器的模型中的工作方式仍不清楚。我们取消了KD的组件，并提出了一个统一的KD框架。通过框架，花费了23,000多个GPU小时的系统和广泛的实验，从知识类型的角度，匹配策略，宽度深度折衷，初始化，型号大小等。在培训前语言模型中，对先前最新的（SOTA）的相对显着改善。最后，我们为基于变压器模型的KD提供了最佳实践指南。

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resourcerestricted devices. To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models. By leveraging this new KD method, the plenty of knowledge encoded in a large "teacher" BERT can be effectively transferred to a small "student" Tiny-BERT. Then, we introduce a new two-stage learning framework for TinyBERT, which performs Transformer distillation at both the pretraining and task-specific learning stages. This framework ensures that TinyBERT can capture the general-domain as well as the task-specific knowledge in BERT. TinyBERT 41 with 4 layers is empirically effective and achieves more than 96.8% the performance of its teacher BERT BASE on GLUE benchmark, while being 7.5x smaller and 9.4x faster on inference. TinyBERT 4 is also significantly better than 4-layer state-of-the-art baselines on BERT distillation, with only ∼28% parameters and ∼31% inference time of them. Moreover, TinyBERT 6 with 6 layers performs on-par with its teacher BERT BASE .

大型的语言模型（PRELMS）正在彻底改变所有基准的自然语言处理。但是，它们的巨大尺寸对于小型实验室或移动设备上的部署而言是过分的。修剪和蒸馏等方法可减少模型尺寸，但通常保留相同的模型体系结构。相反，我们探索了蒸馏预告片中的更有效的架构，单词的持续乘法（CMOW），该构造将每个单词嵌入为矩阵，并使用矩阵乘法来编码序列。我们扩展了CMOW体系结构及其CMOW/CBOW-HYBRID变体，具有双向组件，以提供更具表现力的功能，在预绘制期间进行一般（任务无义的）蒸馏的单次表示，并提供了两种序列编码方案，可促进下游任务。句子对，例如句子相似性和自然语言推断。我们的基于矩阵的双向CMOW/CBOW-HYBRID模型在问题相似性和识别文本范围内的Distilbert具有竞争力，但仅使用参数数量的一半，并且在推理速度方面快三倍。除了情感分析任务SST-2和语言可接受性任务COLA外，我们匹配或超过ELMO的ELMO分数。但是，与以前的跨架结构蒸馏方法相比，我们证明了检测语言可接受性的分数增加了一倍。这表明基于基质的嵌入可用于将大型预赛提炼成竞争模型，并激励朝这个方向进行进一步的研究。

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model. Traditional knowledge distillation methods include response-based methods and feature-based methods. Response-based methods are used the most widely but suffer from lower upper limit of model performance, while feature-based methods have constraints on the vocabularies and tokenizers. In this paper, we propose a tokenizer-free method liberal feature-based distillation (LEAD). LEAD aligns the distribution between teacher model and student model, which is effective, extendable, portable and has no requirements on vocabularies, tokenizer, or model architecture. Extensive experiments show the effectiveness of LEAD on several widely-used benchmarks, including MS MARCO Passage, TREC Passage 19, TREC Passage 20, MS MARCO Document, TREC Document 19 and TREC Document 20.

我们从任务特定的BERT基教师模型执行知识蒸馏（KD）基准到各种学生模型：Bilstm，CNN，Bert-Tiny，Bert-Mini和Bert-small。我们的实验涉及在两个任务中分组的12个数据集：印度尼西亚语言中的文本分类和序列标记。我们还比较蒸馏的各个方面，包括使用Word Embeddings和未标记的数据增强的使用。我们的实验表明，尽管基于变压器的模型的普及程度不断上升，但是使用Bilstm和CNN学生模型，与修剪的BERT模型相比，使用Bilstm和CNN学生模型提供了性能和计算资源（CPU，RAM和存储）之间的最佳权衡。我们进一步提出了一些快速胜利，通过涉及涉及丢失功能，Word Embeddings和未标记的数据准备的简单选择的高效KD培训机制来生产小型NLP模型。

已经证明了对比学习适合学习句子嵌入，可以显着提高语义文本相似性（STS）任务。最近，大型对比学习模型，例如句子T5倾向于学到更强大的句子嵌入。虽然有效，但由于计算资源或时间成本限制，这种大型型号很难在线服务。为了解决这个问题，通常采用知识蒸馏（KD），这可以将大型“教师”模型压缩成一个小的“学生”模型，但通常会遭受一些性能损失。在这里，我们提出了一个增强的KD框架，称为蒸馏 - 对比度（迪斯科）。所提出的迪斯科框架首先利用KD将大句子嵌入模型的能力转移到大型未标记数据的小学生模型，然后在标记的训练数据上具有对比学习的学生模型。对于迪斯科舞厅的KD进程，我们进一步提出了对比的知识蒸馏（CKD），以增强教师模型培训，KD和学生模型的一致性，这可能会提高迅速学习的表现。 7 STS基准测试的广泛实验表明，使用所提出的迪斯科和CKD培训的学生模型很少或甚至没有性能损失，并且始终如一地优于相同参数大小的相应对应物。令人惊讶的是，我们的110米学生模型甚至可以优于最新的最新（SOTA）模型，即句子T5（11B），只有1％的参数。

在生物医学语料库中预先培训的语言模型，例如Biobert，最近在下游生物医学任务上显示出令人鼓舞的结果。另一方面，由于嵌入尺寸，隐藏尺寸和层数等因素，许多现有的预训练模型在资源密集型和计算上都是沉重的。自然语言处理（NLP）社区已经制定了许多策略来压缩这些模型，利用修剪，定量和知识蒸馏等技术，从而导致模型更快，更小，随后更易于使用。同样，在本文中，我们介绍了六种轻型模型，即Biodistilbert，Biotinybert，BioMobilebert，Distilbiobert，Tinybiobert和Cmpactactbiobert，并通过掩护的语言在PubMed DataSet上通过掩护数据进行了知识蒸馏而获得的知识蒸馏来获得。建模（MLM）目标。我们在三个生物医学任务上评估了所有模型，并将它们与Biobert-V1.1进行比较，以创建有效的轻量级模型，以与较大的对应物相同。所有模型将在我们的HuggingFace配置文件上公开可用，网址为https://huggingface.co/nlpie，用于运行实验的代码将在https://github.com/nlpie-research/compact-compact-biomedical-transformers上获得。

Pre-trained language models achieve superior performance, but they are computationally expensive due to their large size. Techniques such as pruning and knowledge distillation (KD) have been developed to reduce their size and latency. In most structural pruning methods, the pruning units, such as attention heads and feed-forward hidden dimensions, only span a small model structure space and limit the structures that the pruning algorithm can explore. In this work, we propose Gradient-based Intra-attention pruning (GRAIN), which inspects fine intra-attention structures, and allows different heads to have different sizes. Intra-attention pruning greatly expands the searching space of model structures and yields highly heterogeneous structures. We further propose structure regularization to encourage generating more regular structures, which achieves higher speedups than heterogeneous ones. We also integrate KD into the pruning process with a gradient separation strategy to reduce the interference of KD with the pruning process. GRAIN is evaluated on a variety of tasks. Results show that it notably outperforms other methods at the same or similar model size. Even under extreme compression where only $3\%$ weights in transformers remain, the pruned model is still competitive.

Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile computing. Efficient NLP research aims to comprehensively consider computation, time and carbon emission for the entire life-cycle of NLP, including data preparation, model training and inference. In this survey, we focus on the inference stage and review the current state of model compression and acceleration for pretrained language models, including benchmarks, metrics and methodology.

迅速调整，它冻结了预审计的语言模型（PLM），只有微调的几个额外软提示的参数，在PLM具有数十亿个参数时，对全参数微调（即模型调整）显示出具有竞争性的性能，但仍然显示出竞争力。在较小的PLM的情况下，性能差。因此，迅速转移（POT），通过训练有素的类似源任务的提示来初始化目标提示，最近提议改善及时调整。但是，这样的香草锅方法通常会实现次优的性能，因为（i）锅对源目标对的相似性和（ii）直接对目标提示进行初始提示的提示敏感，而目标任务可能会导致灾难性忘记来源知识。为了解决这些问题，我们提出了一个新的指标，以准确预测及时的转移性（关于（i）），以及一种利用知识蒸馏技术将“知识”从源提示转移到的新颖的锅方法（即熊猫）目标以微妙的方式提示，并有效缓解灾难性遗忘（关于（ii））。此外，为了实现每个源目标对的自适应及时转移，我们使用指标来控制熊猫方法中的知识转移。对PLM的5个量表的21个源和9个目标数据集的189组组合进行了广泛而系统的实验，表明：1）我们提出的指标很好地预测了及时的可传递性； 2）在所有任务和型号中，我们的熊猫始终优于香草锅的平均得分2.3％（最高24.1％）； 3）通过我们的熊猫方法，及时调整可以比在各种PLM量表场景中的模型调整来实现竞争性甚至更好的性能。接受代码和模型将在接受后发布。

将最新的变压器模型蒸馏成轻量级的学生模型是降低推理时计算成本的有效方法。学生模型通常是紧凑的变压器，参数较少，而昂贵的操作（例如自我发项）持续存在。因此，对于实时或大量用例，提高的推理速度仍然不令人满意。在本文中，我们旨在通过将教师模型提炼成更大，更稀疏的学生模型来进一步推动推理速度的极限 - 更大的是它们扩展到数十亿个参数；稀疏，大多数模型参数是N-gram嵌入。我们对六个单词文本分类任务的实验表明，这些学生模型平均保留了罗伯塔大师教师表现的97％，同时推理时GPU和CPU的加速速度最高为600倍。进一步的调查表明，我们的管道也有助于句子对分类任务和域泛化设置。

机器学习中的知识蒸馏是将知识从名为教师的大型模型转移到一个名为“学生”的较小模型的过程。知识蒸馏是将大型网络（教师）压缩到较小网络（学生）的技术之一，该网络可以部署在手机等小型设备中。当教师和学生之间的网络规模差距增加时，学生网络的表现就会下降。为了解决这个问题，在教师模型和名为助教模型的学生模型之间采用了中间模型，这反过来弥补了教师与学生之间的差距。在这项研究中，我们已经表明，使用多个助教模型，可以进一步改进学生模型（较小的模型）。我们使用加权集合学习将这些多个助教模型组合在一起，我们使用了差异评估优化算法来生成权重值。

Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowledge from a larger model (a teacher). Although KD methods achieve state-of-the-art performance in numerous settings, they suffer from several problems limiting their performance. It is shown in the literature that the capacity gap between the teacher and the student networks can make KD ineffective. Additionally, existing KD techniques do not mitigate the noise in the teacher's output: modeling the noisy behaviour of the teacher can distract the student from learning more useful features. We propose a new KD method that addresses these problems and facilitates the training compared to previous techniques. Inspired by continuation optimization, we design a training procedure that optimizes the highly non-convex KD objective by starting with the smoothed version of this objective and making it more complex as the training proceeds. Our method (Continuation-KD) achieves state-of-the-art performance across various compact architectures on NLU (GLUE benchmark) and computer vision tasks (CIFAR-10 and CIFAR-100).

Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but their high computational costs prevent their use in many real-world applications. In this paper, we explore the following research question: How can we make the AS2 models more accurate without significantly increasing their model complexity? To address the question, we propose a Multiple Heads Student architecture (named CERBERUS), an efficient neural network designed to distill an ensemble of large transformers into a single smaller model. CERBERUS consists of two components: a stack of transformer layers that is used to encode inputs, and a set of ranking heads; unlike traditional distillation technique, each of them is trained by distilling a different large transformer architecture in a way that preserves the diversity of the ensemble members. The resulting model captures the knowledge of heterogeneous transformer models by using just a few extra parameters. We show the effectiveness of CERBERUS on three English datasets for AS2; our proposed approach outperforms all single-model distillations we consider, rivaling the state-of-the-art large AS2 models that have 2.7x more parameters and run 2.5x slower. Code for our model is available at https://github.com/amazon-research/wqa-cerberus

尽管配备的远景和语言预处理（VLP）在过去两年中取得了显着的进展，但它遭受了重大缺点：VLP型号不断增加的尺寸限制了其部署到现实世界的搜索场景（高潜伏期是不可接受的）。为了减轻此问题，我们提出了一种新颖的插件动态对比度蒸馏（DCD）框架，以压缩ITR任务的大型VLP模型。从技术上讲，我们面临以下两个挑战：1）由于GPU内存有限，在处理交叉模式融合功能期间优化了太多的负样本，因此很难直接应用于跨模式任务，因此很难直接应用于跨模式任务。 。 2）从不同的硬样品中静态优化学生网络的效率效率低下，这些样本对蒸馏学习和学生网络优化具有不同的影响。我们试图从两点克服这些挑战。首先，为了实现多模式对比度学习并平衡培训成本和效果，我们建议使用教师网络估算学生的困难样本，使学生吸收了预培训的老师的强大知识，并掌握知识来自硬样品。其次，要从硬样品对学习动态，我们提出动态蒸馏以动态学习不同困难的样本，从更好地平衡知识和学生的自学能力的困难的角度。我们成功地将我们提出的DCD策略应用于两个最先进的视觉语言预处理模型，即vilt和仪表。关于MS-Coco和FlickR30K基准测试的广泛实验显示了我们DCD框架的有效性和效率。令人鼓舞的是，与现有的ITR型号相比，我们可以至少加快推断至少129美元的$ \ times $。

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolutionfree transformers trained on ImageNet only using a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.We also introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention, typically from a convnet teacher. The learned transformers are competitive (85.2% top-1 acc.) with the state of the art on ImageNet, and similarly when transferred to other tasks. We will share our code and models.

由于学术和工业领域的异质图无处不在，研究人员最近提出了许多异质图神经网络（HGNN）。在本文中，我们不再采用更强大的HGNN模型，而是有兴趣设计一个多功能的插件模块，该模块解释了从预先训练的HGNN中提取的关系知识。据我们所知，我们是第一个在异质图上提出高阶（雇用）知识蒸馏框架的人，无论HGNN的模型体系结构如何，它都可以显着提高预测性能。具体而言，我们的雇用框架最初执行一阶节点级知识蒸馏，该蒸馏曲线及其预测逻辑编码了老师HGNN的语义。同时，二阶关系级知识蒸馏模仿了教师HGNN生成的不同类型的节点嵌入之间的关系相关性。在各种流行的HGNN模型和三个现实世界的异质图上进行了广泛的实验表明，我们的方法获得了一致且相当大的性能增强，证明了其有效性和泛化能力。

知识蒸馏已成为获得紧凑又有效模型的重要方法。为实现这一目标，培训小型学生模型以利用大型训练有素的教师模型的知识。然而，由于教师和学生之间的能力差距，学生的表现很难达到老师的水平。关于这个问题，现有方法建议通过代理方式减少教师知识的难度。我们认为这些基于代理的方法忽视了教师的知识损失，这可能导致学生遇到容量瓶颈。在本文中，我们从新的角度来缓解能力差距问题，以避免知识损失的目的。我们建议通过对抗性协作学习建立一个更有力的学生，而不是牺牲教师的知识。为此，我们进一步提出了一种逆势协作知识蒸馏（ACKD）方法，有效提高了知识蒸馏的性能。具体来说，我们用多个辅助学习者构建学生模型。同时，我们设计了对抗的对抗性协作模块（ACM），引入注意机制和对抗的学习，以提高学生的能力。四个分类任务的广泛实验显示了拟议的Ackd的优越性。

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolution-free transformers by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

知识蒸馏（KD），最称为模型压缩的有效方法，旨在将更大的网络（教师）的知识转移到更小的网络（学生）。传统的KD方法通常采用以监督方式培训的教师模型，其中输出标签仅作为目标处理。我们进一步扩展了这一受监督方案，我们为KD，即Oracle老师推出了一种新型的教师模型，它利用源输入和输出标签的嵌入来提取更准确的知识来转移到学生。所提出的模型遵循变压器网络的编码器解码器注意结构，这允许模型从输出标签上参加相关信息。在三种不同的序列学习任务中进行了广泛的实验：语音识别，场景文本识别和机器翻译。从实验结果来看，我们经验证明，拟议的模型在这些任务中改善了学生，同时在教师模型的培训时间内实现了相当大的速度。