Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting, focusing on Transformer models for NLP tasks that are limited by compute: self-supervised pretraining and high-resource machine translation. We first show that even though smaller Transformer models execute faster per iteration, wider and deeper models converge in significantly fewer steps. Moreover, this acceleration in convergence typically outpaces the additional computational overhead of using larger models. Therefore, the most compute-efficient training strategy is to counterintuitively train extremely large models but stop after a small number of iterations. This leads to an apparent trade-off between the training efficiency of large Transformer models and the inference efficiency of small Transformer models. However, we show that large models are more robust to compression techniques such as quantization and pruning than small models. Consequently, one can get the best of both worlds: heavily compressed, large models achieve higher accuracy than lightly compressed, small models.

相关内容

ACM/IEEE第23届模型驱动工程语言和系统国际会议，是模型驱动软件和系统工程的首要会议系列，由ACM-SIGSOFT和IEEE-TCSE支持组织。自1998年以来，模型涵盖了建模的各个方面，从语言和方法到工具和应用程序。模特的参加者来自不同的背景，包括研究人员、学者、工程师和工业专业人士。MODELS 2019是一个论坛，参与者可以围绕建模和模型驱动的软件和系统交流前沿研究成果和创新实践经验。今年的版本将为建模社区提供进一步推进建模基础的机会，并在网络物理系统、嵌入式系统、社会技术系统、云计算、大数据、机器学习、安全、开源等新兴领域提出建模的创新应用以及可持续性。 官网链接：http://www.modelsconference.org/

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. In the first stage, we sufficiently widen the deep thin network and train it until convergence. In the second stage, we use this well-trained deep wide network to warm up (or initialize) the original deep thin network. This is achieved by letting the thin network imitate the immediate outputs of the wide network from layer to layer. In the last stage, we further fine tune this well initialized deep thin network. The theoretical guarantee is established by using mean field analysis, which shows the advantage of layerwise imitation over traditional training deep thin networks from scratch by backpropagation. We also conduct large-scale empirical experiments to validate our approach. By training with our method, ResNet50 can outperform ResNet101, and BERT_BASE can be comparable with BERT_LARGE, where both the latter models are trained via the standard training procedures as in the literature.

The demand for artificial intelligence has grown significantly over the last decade and this growth has been fueled by advances in machine learning techniques and the ability to leverage hardware acceleration. However, in order to increase the quality of predictions and render machine learning solutions feasible for more complex applications, a substantial amount of training data is required. Although small machine learning models can be trained with modest amounts of data, the input for training larger models such as neural networks grows exponentially with the number of parameters. Since the demand for processing training data has outpaced the increase in computation power of computing machinery, there is a need for distributing the machine learning workload across multiple machines, and turning the centralized into a distributed system. These distributed systems present new challenges, first and foremost the efficient parallelization of the training process and the creation of a coherent model. This article provides an extensive overview of the current state-of-the-art in the field by outlining the challenges and opportunities of distributed machine learning over conventional (centralized) machine learning, discussing the techniques used for distributed machine learning, and providing an overview of the systems that are available.

A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). The model was trained on the inverted Stanford Question Answering Dataset (SQuAD), which is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles. After training, the question generation model is able to generate simple questions relevant to unseen passages and answers containing an average of 8 words per question. The word error rate (WER) was used as a metric to compare the similarity between SQuAD questions and the model-generated questions. Although the high average WER suggests that the questions generated differ from the original SQuAD questions, the questions generated are mostly grammatically correct and plausible in their own right.

Deep convolutional neural networks (CNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past few years, tremendous progress has been made in this area. In this paper, we survey the recent advanced techniques for compacting and accelerating CNNs model developed. These techniques are roughly categorized into four schemes: parameter pruning and sharing, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and sharing will be described at the beginning, after that the other techniques will be introduced. For each scheme, we provide insightful analysis regarding the performance, related applications, advantages, and drawbacks etc. Then we will go through a few very recent additional successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrix, the main datasets used for evaluating the model performance and recent benchmarking efforts. Finally, we conclude this paper, discuss remaining challenges and possible directions on this topic.

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters. Source code is at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet.

Recent works have highlighted the strengths of the Transformer architecture for dealing with sequence tasks. At the same time, neural architecture search has advanced to the point where it can outperform human-designed models. The goal of this work is to use architecture search to find a better Transformer architecture. We first construct a large search space inspired by the recent advances in feed-forward sequential models and then run evolutionary architecture search, seeding our initial population with the Transformer. To effectively run this search on the computationally expensive WMT 2014 English-German translation task, we develop the progressive dynamic hurdles method, which allows us to dynamically allocate more resources to more promising candidate models. The architecture found in our experiments - the Evolved Transformer - demonstrates consistent improvement over the Transformer on four well-established language tasks: WMT 2014 English-German, WMT 2014 English-French, WMT 2014 English-Czech and LM1B. At big model size, the Evolved Transformer is twice as efficient as the Transformer in FLOPS without loss in quality. At a much smaller - mobile-friendly - model size of ~7M parameters, the Evolved Transformer outperforms the Transformer by 0.7 BLEU on WMT'14 English-German.

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs). Inspired by the success of Transformer network in neural machine translation (NMT), in this paper, we introduce and adapt the multi-head attention mechanism to replace the RNN structures and also the original attention mechanism in Tacotron2. With the help of multi-head self-attention, the hidden states in the encoder and decoder are constructed in parallel, which improves the training efficiency. Meanwhile, any two inputs at different times are connected directly by self-attention mechanism, which solves the long range dependency problem effectively. Using phoneme sequences as input, our Transformer TTS network generates mel spectrograms, followed by a WaveNet vocoder to output the final audio results. Experiments are conducted to test the efficiency and performance of our new network. For the efficiency, our Transformer TTS network can speed up the training about 4.25 times faster compared with Tacotron2. For the performance, rigorous human tests show that our proposed model achieves state-of-the-art performance (outperforms Tacotron2 with a gap of 0.048) and is very close to human quality (4.39 vs 4.44 in MOS).

For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit sphere, as opposed to the entire space, and the threshold can be trained in a bounded interval, as opposed to the real line. We show that the NNs in the reduced parameter space are mathematically equivalent to the standard NNs with parameters in the whole space. The reduced parameter space shall facilitate the optimization procedure for the network training, as the search space becomes (much) smaller. We demonstrate the improved training performance using numerical examples.

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce \emph{Kardam}, the first distributed asynchronous stochastic gradient descent (SGD) algorithm that copes with Byzantine workers. Kardam consists of two complementary components: a filtering and a dampening component. The first is scalar-based and ensures resilience against $\frac{1}{3}$ Byzantine workers. Essentially, this filter leverages the Lipschitzness of cost functions and acts as a self-stabilizer against Byzantine workers that would attempt to corrupt the progress of SGD. The dampening component bounds the convergence rate by adjusting to stale information through a generic gradient weighting scheme. We prove that Kardam guarantees almost sure convergence in the presence of asynchrony and Byzantine behavior, and we derive its convergence rate. We evaluate Kardam on the CIFAR-100 and EMNIST datasets and measure its overhead with respect to non Byzantine-resilient solutions. We empirically show that Kardam does not introduce additional noise to the learning procedure but does induce a slowdown (the cost of Byzantine resilience) that we both theoretically and empirically show to be less than $f/n$, where $f$ is the number of Byzantine failures tolerated and $n$ the total number of workers. Interestingly, we also empirically observe that the dampening component is interesting in its own right for it enables to build an SGD algorithm that outperforms alternative staleness-aware asynchronous competitors in environments with honest workers.

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time by solely using attention. Motivated by the Transformer, Directional Self Attention Network (Shen et al., 2017), a fully attention-based sentence encoder, was proposed. It showed good performance with various data by using forward and backward directional information in a sentence. But in their study, not considered at all was the distance between words, an important feature when learning the local dependency to help understand the context of input text. We propose Distance-based Self-Attention Network, which considers the word distance by using a simple distance mask in order to model the local dependency without losing the ability of modeling global dependency which attention has inherent. Our model shows good performance with NLI data, and it records the new state-of-the-art result with SNLI data. Additionally, we show that our model has a strength in long sentences or documents.

Denny Zhou,Mao Ye,Chen Chen,Tianjian Meng,Mingxing Tan,Xiaodan Song,Quoc Le,Qiang Liu,Dale Schuurmans
11+阅读 · 2020年7月1日
Joost Verbraeken,Matthijs Wolting,Jonathan Katzy,Jeroen Kloppenburg,Tim Verbelen,Jan S. Rellermeyer
22+阅读 · 2019年12月20日
Kettip Kriangchaivech,Artit Wangperawong
3+阅读 · 2019年9月14日
Yu Cheng,Duo Wang,Pan Zhou,Tao Zhang
32+阅读 · 2019年9月8日
Mingxing Tan,Quoc V. Le
3+阅读 · 2019年5月28日
David R. So,Chen Liang,Quoc V. Le
4+阅读 · 2019年1月30日
Naihan Li,Shujie Liu,Yanqing Liu,Sheng Zhao,Ming Liu,Ming Zhou
3+阅读 · 2018年11月13日
Tong Qin,Ling Zhou,Dongbin Xiu
3+阅读 · 2018年8月17日
Georgios Damaskinos,El Mahdi El Mhamdi,Rachid Guerraoui,Rhicheek Patra,Mahsa Taziki
3+阅读 · 2018年7月9日
Jinbae Im,Sungzoon Cho
10+阅读 · 2017年12月6日

17+阅读 · 2019年6月9日
CreateAMind
9+阅读 · 2019年5月22日
CreateAMind
6+阅读 · 2019年5月18日
CreateAMind
4+阅读 · 2019年1月18日
CreateAMind
26+阅读 · 2019年1月3日

10+阅读 · 2018年12月24日

22+阅读 · 2017年11月16日

22+阅读 · 2017年11月5日
CreateAMind
5+阅读 · 2017年8月4日
Top