Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. A knowledge distillation approach addresses the computational efficiency by self-distilling BERT into a smaller transformer representation having fewer layers and smaller internal embedding. However, the performance of these models drops as we reduce the number of layers, notably in advanced NLP tasks such as span question answering. In addition, a separate model must be trained for each inference scenario with its distinct computational budget. Dynamic-TinyBERT tackles both limitations by partially implementing the Length Adaptive Transformer (LAT) technique onto TinyBERT, achieving x3 speedup over BERT-base with minimal accuracy loss. In this work, we expand the Dynamic-TinyBERT approach to generate a much more highly efficient model. We use MiniLM distillation jointly with the LAT method, and we further enhance the efficiency by applying low-bit quantization. Our quantized length-adaptive MiniLM model (QuaLA-MiniLM) is trained only once, dynamically fits any inference scenario, and achieves an accuracy-efficiency trade-off superior to any other efficient approaches per any computational budget on the SQuAD1.1 dataset (up to x8.8 speedup with <1% accuracy loss). The code to reproduce this work is publicly available on Github.

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime. Source code is publicly available at https://github.com/intel/intel-extension-for-transformers.

最近的几种方法，例如参数有效的微调（PEFT）和模式开发训练（PET），在标签筛选设置中取得了令人印象深刻的结果。但是，它们很难使用，因为它们会受到手动制作的提示的高度可变性，并且通常需要十亿参数语言模型才能达到高精度。为了解决这些缺点，我们提出了SETFIT（句子变压器微调），这是一个有效且迅速的框架，用于对句子变形金刚（ST）进行几次微调。 SetFit首先以对比的暹罗方式对少数文本对进行微调验证的st。然后将所得模型用于生成丰富的文本嵌入，这些嵌入方式用于训练分类头。这个简单的框架不需要任何提示或口头化，并且比现有技术少的参数较少，因此可以实现高精度。我们的实验表明，SetFit通过PEFT和PET技术获得了可比的结果，同时训练的速度更快。我们还表明，SETFIT可以通过简单地切换ST主体来应用于多语言设置。我们的代码可从https://github.com/huggingface/setFit以及我们的数据集获得，网址为https://huggingface.co/setfit。

有限的计算预算通常会阻止变压器在生产中使用，并且利用高精度。 Tinybert通过将熔点蒸馏出来的较小变压器表示来解决具有较少层和更小的内部嵌入的较小变压器表示来解决计算效率。然而，当我们将层数减少50％时，Tinybert的性能下降，并且当我们将层数减少75％的高级NLP任务时，如跨度问题的接听。此外，必须为每个推理方案培训单独的型号，其中包括不同的计算预算。在这项工作中，我们呈现动态 - Tinybert，一个小博特模型，利用序列长度减小和Quand参数优化，以获得每个计算预算的增强推理效率。动态 - Tinybert仅培训一次，使用BERT进行，实现精度加速，优于任何其他有效的方法（高达3.3倍，损耗<1％）。出版后，重现我们工作的代码将是开放的。

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。

Graph Neural Networks (GNNs) are prominent in handling sparse and unstructured data efficiently and effectively. Specifically, GNNs were shown to be highly effective for node classification tasks, where labelled information is available for only a fraction of the nodes. Typically, the optimization process, through the objective function, considers only labelled nodes while ignoring the rest. In this paper, we propose novel objective terms for the training of GNNs for node classification, aiming to exploit all the available data and improve accuracy. Our first term seeks to maximize the mutual information between node and label features, considering both labelled and unlabelled nodes in the optimization process. Our second term promotes anisotropic smoothness in the prediction maps. Lastly, we propose a cross-validating gradients approach to enhance the learning from labelled data. Our proposed objectives are general and can be applied to various GNNs and require no architectural modifications. Extensive experiments demonstrate our approach using popular GNNs like GCN, GAT and GCNII, reading a consistent and significant accuracy improvement on 10 real-world node classification datasets.

We present a new pre-trained language model (PLM) for modern Hebrew, termed AlephBERTGimmel, which employs a much larger vocabulary (128K items) than standard Hebrew PLMs before. We perform a contrastive analysis of this model against all previous Hebrew PLMs (mBERT, heBERT, AlephBERT) and assess the effects of larger vocabularies on task performance. Our experiments show that larger vocabularies lead to fewer splits, and that reducing splits is better for model performance, across different tasks. All in all this new model achieves new SOTA on all available Hebrew benchmarks, including Morphological Segmentation, POS Tagging, Full Morphological Analysis, NER, and Sentiment Analysis. Subsequently we advocate for PLMs that are larger not only in terms of number of layers or training data, but also in terms of their vocabulary. We release the new model publicly for unrestricted use.

Deep neural networks (DNNs) have greatly impacted numerous fields over the past decade. Yet despite exhibiting superb performance over many problems, their black-box nature still poses a significant challenge with respect to explainability. Indeed, explainable artificial intelligence (XAI) is crucial in several fields, wherein the answer alone -- sans a reasoning of how said answer was derived -- is of little value. This paper uncovers a troubling property of explanation methods for image-based DNNs: by making small visual changes to the input image -- hardly influencing the network's output -- we demonstrate how explanations may be arbitrarily manipulated through the use of evolution strategies. Our novel algorithm, AttaXAI, a model-agnostic, adversarial attack on XAI algorithms, only requires access to the output logits of a classifier and to the explanation map; these weak assumptions render our approach highly useful where real-world models and data are concerned. We compare our method's performance on two benchmark datasets -- CIFAR100 and ImageNet -- using four different pretrained deep-learning models: VGG16-CIFAR100, VGG16-ImageNet, MobileNet-CIFAR100, and Inception-v3-ImageNet. We find that the XAI methods can be manipulated without the use of gradients or other model internals. Our novel algorithm is successfully able to manipulate an image in a manner imperceptible to the human eye, such that the XAI method outputs a specific explanation map. To our knowledge, this is the first such method in a black-box setting, and we believe it has significant value where explainability is desired, required, or legally mandatory.

结肠镜检查是一种常规门诊手术，用于检查结肠和直肠的任何异常，包括息肉，憩室和结肠结构的狭窄。临床医生的大量时间用于在结肠镜检查过程中拍摄的快照，以维持医疗记录或进一步研究。自动化此步骤可以节省时间并提高流程的效率。在我们的工作中，我们收集了一个由专家注释的过程中的120个结肠镜检查视频和2416张快照的数据集。此外，我们开发了一种基于新颖的，视觉转化器的地标检测算法，该算法可以从结肠镜检查过程中鉴定出关键的解剖标志（阑尾孔，回肠瓣膜/盲肠地标和直肠翻新）。我们的算法在预处理过程中使用自适应伽马校正，以保持所有图像的一致亮度。然后，我们将视觉变压器用作特征提取主链和完全连接的基于网络的分类器头，将给定的框架分为四个类：三个地标或非地标框架。我们将视觉变压器（VIT-B/16）主链与RESNET-101和Convnext-B骨干进行了比较，这些骨干和Convnext-B骨干也接受了类似训练。我们报告了快照的测试数据集上的视觉变压器主链的精度为82％。

进化计算（EC）已被证明能够快速训练深人造神经网络（DNNS）来解决增强学习（RL）问题。虽然遗传算法（GA）非常适合利用既不具有欺骗性也不稀疏的奖励功能，但当奖励函数是这些功能时，它会挣扎。为此，在某些情况下，新颖的搜索（NS）已被证明能够超越梯度跟随优化器，而在其他情况下则表现不佳。我们提出了一种新算法：探索 - 探索$ \ gamma $ - 适应学习者（$ e^2 \ gamma al $或eyal）。通过保留动态大小的寻求新颖的代理商的利基市场，该算法可以维持人口多样性，并在可能的情况下利用奖励信号并探索其他奖励信号。该算法将GA的剥削能力和NS的勘探能力结合在一起，同时保持其简单性和优雅性。我们的实验表明，在大多数情况下，Eyal在与GA相当的情况下都胜过NS - 在某些情况下，它可以均优于两者。 Eyal还允许用其他算法（例如演化策略和惊喜搜索）代替利用组件（GA）和探索组件（NS）（NS），从而为未来的研究打开了大门。