Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset. Alternatively, one may directly work on the improvement of the optimization procedure of the compact model toward better generalization. Recent works observe that the flatness of the local minimum correlates well with better generalization. In this work, we adapt Stochastic Weight Averaging (SWA), a method encouraging convergence to a flatter minimum, to fine-tuning PLMs. We conduct extensive experiments on various NLP tasks (text classification, question answering, and generation) and different model architectures and demonstrate that our adaptation improves the generalization without extra computation cost. Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.

基于变压器的语言模型应用于自然语言处理的广泛应用程序。但是，它们效率低，难以部署。近年来，已经提出了许多压缩算法来提高目标硬件上大型变压器的模型的实现效率。在这项工作中，我们通过整合体重修剪和模型蒸馏来提出一种训练稀疏预训练的变压器语言模型的新方法。这些稀疏的预训练型号可用于在维护稀疏模式的同时传输广泛的任务。我们展示了我们有三个已知的架构的方法，以创建稀疏的预训练伯特基，BERT-MAT​​RY和DISTOLBERT。我们展示了压缩稀疏的预训练模型如何培训他们的知识，以最小的精度损失将他们的知识转移到五种不同的下游自然语言任务。此外，我们展示了如何使用量化感知培训进一步将稀疏模型的重量压缩为8位精度。例如，在SQUAdv1.1上使用我们稀疏预训练的BERT频率，并量化为8位，我们为编码器达到40美元的压缩比，而不是1 \％$精度损失。据我们所知，我们的结果表明Bert-Base，Bert-Light和Distilbert的最佳压缩至准确率。

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 .

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。

Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs better on multitask few-shot learning but also requires more computation than Meta-ICT. Our method shows consistent improvements for both Meta-ICT and Multitask-ICT on two benchmarks: LAMA and CrossFit. Our extensive experiments and analysis reveal that in-context learning objectives and language modeling objectives are complementary under the Multitask-ICT paradigm. In-context learning objectives achieve the best performance when combined with language modeling objectives.

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).

We revisit the performance of the classic gradual magnitude pruning (GMP) baseline for large language models, focusing on the classic BERT benchmark on various popular tasks. Despite existing evidence in the literature that GMP performs poorly, we show that a simple and general variant, which we call GMP*, can match and sometimes outperform more complex state-of-the-art methods. Our results provide a simple yet strong baseline for future work, highlight the importance of parameter tuning for baselines, and even improve the performance of the state-of-the-art second-order pruning method in this setting.

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

深度神经网络通常过度分辨，并且可能不容易实现模型泛化。对抗性训练通过规则地改变普遍选择的扰动之外的损失变化来提高普遍性的效果。最近提出的清晰度感知最小化（SAM）算法采用对抗性重量扰动，鼓励模型收敛于扁平最小值。遗憾的是，由于计算成本增加，对抗性重量扰动只能有效地近似于每批次而不是每个实例，导致性能下降。在本文中，我们提出了在每个批处理中动态重新缓解的扰动，其中揭开的实例被加权，可以用作每个实例扰动的更好近似。我们提出了充满活力的重新重量（{\ Delta} -Sam）的清晰度感知最小化，这实现了高效的防护估计的想法。胶水基准测试的实验证明了{\ delta} -sam的有效性。

This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks, including question answering, natural language inference, word sense disambiguation, coreference resolution, and reasoning. [Method] Instead of arbitrarily increasing the size of a pretrained language model (PLM), our aim is to 1) fully extract knowledge from the input pretraining data given a certain parameter budget, e.g., 6B, and 2) effectively transfer this knowledge to downstream tasks. To achieve goal 1), we propose self-evolution learning for PLMs to wisely predict the informative tokens that should be masked, and supervise the masked language modeling (MLM) process with rectified smooth labels. For goal 2), we leverage the prompt transfer technique to improve the low-resource tasks by transferring the knowledge from the foundation model and related downstream tasks to the target task. [Results] According to our submission record (Oct. 2022), with our optimized pretraining and fine-tuning strategies, our 6B Vega method achieved new state-of-the-art performance on 4/8 tasks, sitting atop the SuperGLUE leaderboard on Oct. 8, 2022, with an average score of 91.3.

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。

Language models with the Transformers structure have shown great performance in natural language processing. However, there still poses problems when fine-tuning pre-trained language models on downstream tasks, such as over-fitting or representation collapse. In this work, we propose HyPe, a simple yet effective fine-tuning technique to alleviate such problems by perturbing hidden representations of Transformers layers. Unlike previous works that only add noise to inputs or parameters, we argue that the hidden representations of Transformers layers convey more diverse and meaningful language information. Therefore, making the Transformers layers more robust to hidden representation perturbations can further benefit the fine-tuning of PLMs en bloc. We conduct extensive experiments and analyses on GLUE and other natural language inference datasets. Results demonstrate that HyPe outperforms vanilla fine-tuning and enhances generalization of hidden representations from different layers. In addition, HyPe acquires negligible computational overheads, and is better than and compatible with previous state-of-the-art fine-tuning techniques.

域的概括旨在学习一个可以很好地概括在看不见的测试数据集（即分布数据集）上的模型，该数据与培训数据集不同。为了解决计算机视觉中的领域概括，我们将损失景观理论引入该领域。具体而言，我们从损失景观的角度从四个方面（包括骨干，正则化，训练范式和学习率）引起了深度学习模型的概括能力。我们通过进行广泛的消融研究和可视化来验证有关NICO ++，PAC和VLCS数据集的提议理论。此外，我们将该理论应用于ECCV 2022 NICO挑战1，并在不使用任何域不变方法的情况下获得第三名。

预训练的语言模型（PLM）在自然语言生成（NLG）任务中取得了显着的成功。到目前为止，大多数PLM都使用大型一般语料库以无监督的方式进行了预培训。同时，与无监督的模型相比，预先训练的模型越来越多地显示出较低的数据表现出色。受监督预训练的成功的激励，我们提出了自然语言生成的多任务监督预训练（MVP）。为了预先培训文本生成模型MVP，我们从七个生成任务中收集了45个数据集的标记预训练语料库。对于每个任务，我们进一步预先训练特定的软提示，以刺激执行特定任务的模型能力。广泛的实验证明了我们在许多NLG任务中有监督的预训练的有效性，并且我们的一般方法在17个数据集中的12个中实现了最先进的性能。

半监督学习（SSL）在许多应用领域中已经取得了成功，但这种成功经常涉及任务特定的未标记数据的可用性。知识蒸馏（KD）能够有效地优化紧凑的神经网络，当通过新鲜任务特定的未标记数据蒸馏昂贵的网络时，实现了最佳结果。但是，任务特定的未标记数据可能具有挑战性，特别是对于NLP。我们调查使用生成模型在合成未标记数据中的使用，并呈现一个名为“生成，注释和学习（GAL）”的简单和一般框架。语言模型（LM）用于扫描域中的未标记数据。然后，分类器用于注释这样的数据。最后，综合生成和注释的数据用于推进SSL，KD和NLP和表格任务的几次拍摄学习。为了获得强大的任务特定的LM，我们要么微调来自特定任务的输入的大LM，或者提示具有少数输入示例的大型LM，并且有条件地生成更明显的示例。它还为胶水排行榜上的6层变压器产生了一种新的最先进的。最后，使用GAL的自我训练从UCI存储库的四个表格任务上提供大的收益。

通过微调将大规模的预训练语言模型适应下游任务是实现NLP基准测试最先进性能的标准方法。然而，微调具有数百万或数十亿个参数的所有重量模型是对低资源设置中不稳定的采样低效，并且浪费，因为它需要为每个任务存储模型的单独副本。最近的工作已经开发了参数高效的微调方法，但这些方法仍然需要相对大量的参数或表现不足标准微调。在这项工作中，我们提出了一种特殊调整大型语言模型的方法，其在任务性能和比率参数之间具有更好的权衡的方法，而不是比上事先工作。 Compacter通过构建适配器，低级优化和参数化超复分乘法层的思想之上来实现这一目标。具体地，Compacter将特定于特定的权重矩阵插入到预估计模型的权重中，这些权重被有效地计算为共享的“慢速”权重和“快速”等级 - 每个Compacter层定义的矩阵之间的矩阵产品的总和。仅通过培训0.047％的预磨料模型的参数，Compacter会在胶水上标准微调和胜过标准微调的标准微调和低资源设置。我们的代码在〜\ url {https://github.com/rabeehk/compacter}上公开使用。

用于预培训语言模型的自我监督学习的核心包括预训练任务设计以及适当的数据增强。语言模型中的大多数数据增强都是独立于上下文的。最近在电子中提出了一个开创性的增强，并通过引入辅助生成网络（发电机）来实现最先进的性能，以产生用于培训主要辨别网络（鉴别者）的上下文化数据增强。然而，这种设计引入了发电机的额外计算成本，并且需要调整发电机和鉴别器之间的相对能力。在本文中，我们提出了一种自增强策略（SAS），其中单个网络用于审视以后的时期的培训常规预训练和上下文化数据增强。基本上，该策略消除了单独的发电机，并使用单个网络共同执行具有MLM（屏蔽语言建模）和RTD（替换令牌检测）头的两个预训练任务。它避免了寻找适当大小的发电机的挑战，这对于在电子中证明的性能至关重要，以及其随后的变体模型至关重要。此外，SAS是一项常规策略，可以与最近或将来的许多新技术无缝地结合，例如杜伯塔省的解除关注机制。我们的实验表明，SAS能够在具有相似或更少的计算成本中优于胶水任务中的电磁和其他最先进的模型。

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。

基于变压器的NLP模型是使用数亿甚至数十亿个参数训练的，从而限制了其在计算受限环境中的适用性。尽管参数的数量通常与性能相关，但尚不清楚下游任务是否需要整个网络。在最新的修剪和提炼预培训模型的工作中，我们探索了在预训练模型中放下层的策略，并观察修剪对下游胶水任务的影响。我们能够修剪Bert，Roberta和XLNet型号高达40％，同时保持其原始性能的98％。此外，我们证明，在大小和性能方面，您的修剪模型与使用知识蒸馏的型号相提并论。我们的实验产生有趣的观察结果，例如（i）下层对于维持下游任务性能最重要，（ii）某些任务（例如释义检测和句子相似性）对于降低层的降低和（iii）经过训练的模型更强大。使用不同的目标函数表现出不同的学习模式，并且层掉落。

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-theedge and/or under constrained computational training or inference budgets remains challenging. In this work, we propose a method to pre-train a smaller generalpurpose language representation model, called DistilBERT, which can then be finetuned with good performances on a wide range of tasks like its larger counterparts. While most prior work investigated the use of distillation for building task-specific models, we leverage knowledge distillation during the pre-training phase and show that it is possible to reduce the size of a BERT model by 40%, while retaining 97% of its language understanding capabilities and being 60% faster. To leverage the inductive biases learned by larger models during pre-training, we introduce a triple loss combining language modeling, distillation and cosine-distance losses. Our smaller, faster and lighter model is cheaper to pre-train and we demonstrate its capabilities for on-device computations in a proof-of-concept experiment and a comparative on-device study.