Transformers are one of the most important machine learning workloads today. Training one is a very compute-intensive task, often taking days or weeks, and significant attention has been given to optimizing transformers. Despite this, existing implementations do not efficiently utilize GPUs. We find that data movement is the key bottleneck when training. Due to Amdahl's Law and massive improvements in compute performance, training has now become memory-bound. Further, existing frameworks use suboptimal data layouts. Using these insights, we present a recipe for globally optimizing data movement in transformers. We reduce data movement by up to 22.91% and overall achieve a 1.30x performance improvement over state-of-the-art frameworks when training a BERT encoder layer and 1.19x for the entire BERT. Our approach is applicable more broadly to optimizing deep neural networks, and offers insight into how to tackle emerging performance bottlenecks.
Northeastern University（东北大学）；The Chinese University of Hong Kong（香港中文大学）；NiuTrans Research（小牛翻译研究院）
Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or dependent on hardware. In this paper, we show that the efficiency of Transformer can be improved by combining some simple and hardware-agnostic methods, including tuning hyper-parameters, better design choices and training strategies. On the WMT news translation tasks, we improve the inference efficiency of a strong Transformer system by 3.80X on CPU and 2.…
Informatics Institute（信息学研究所）；University of Amsterdam（阿姆斯特丹大学）
Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation. While the Transformer model has achieved significant improvements for many language pairs and has become the de facto mainstream architecture, its capability under low-resource conditions has not been fully investigated yet. Our experiments on different subsets of the IWSLT14 training data show that the effectiveness of Transformer under low-resource conditions is highly dependent on the hyper-parameter settings. Our experiments show that using an optim…
The Transformer architecture revolutionized the field of natural language processing (NLP). Transformers-based models (e.g., BERT) power many important Web services, such as search, translation, question-answering, etc. While enormous research attention is paid to the training of those models, relatively little efforts are made to improve their inference performance. This paper comes to address this gap by presenting an empirical analysis of scalability and performance of inferencing a Transformer-based model on CPUs. Focusing on the highly popular BERT model, we identify key components of the…
MoE-TransMov: A Transformer-based Model for Next POI Prediction in Familiar & Unfamiliar Movements
Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, IN, USA（普渡大学土木与建设工程学院）；LY Corporation, Tokyo, Japan（东京LY公司）；Tandon School of Engineering, New York University, New York, NY, USA（纽约大学塔能工程学院）
Optimizing Emotion Recognition with Wearable Sensor Data: Unveiling Patterns in Body Movements and Heart Rate through Random Forest Hyperparameter Tuning
Borealis AI；University of Waterloo（滑铁卢大学）；University of Alberta（阿尔伯塔大学）；McGill University（麦吉尔大学）；Mila（米拉人工智能研究所）
It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension. In particular, we successfully train $48$ layers of transformers, comprising $24$ fine-tune…
EEG-based AI-BCI Wheelchair Advancement: Transformer-Based Learning with Motor Imagery for Brain Computer Interface
Department of Computer Science and Engineering, Kathmandu University（加德满都大学计算机科学与工程系）；Department of Electronics and Communication Engineering, Nepal Engineering College, Pokhara University（博卡拉大学尼泊尔工程学院电子与通信工程系）；Department of Applied Sciences and Chemical Engineering, Institute of Engineering, Pulchowk Campus, Tribhuvan University（特里布万大学工程学院普尔乔克校区应用科学与化学工程系）
Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
Department of Psychological & Brain Sciences, University of California, Santa Barbara（加州大学圣塔芭芭拉分校心理与脑科学系）
Humans process visual information with varying resolution (foveated visual system) and explore images by orienting through eye movements the high-resolution fovea to points of interest. The Bayesian ideal searcher (IS) that employs complete knowledge of task-relevant information optimizes eye movement strategy and achieves the optimal search performance. The IS can be employed as an important tool to evaluate the optimality of human eye movements, and potentially provide guidance to improve human observer visual search strategies. Najemnik and Geisler (2005) derived an IS for backgrounds of sp…
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Fraunhofer Heinrich-Hertz-Institute（弗劳恩霍夫海因茨·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））
Parkinson's disease (PD) is a neurological disorder that has a variety of observable motor-related symptoms such as slow movement, tremor, muscular rigidity, and impaired posture. PD is typically diagnosed by evaluating the severity of motor impairments according to scoring systems such as the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Automated severity prediction using video recordings of individuals provides a promising route for non-intrusive monitoring of motor impairments. However, the limited size of PD gait data hinders model ability and clinical po…
Transformers \citep{vaswani2017attention} have gradually become a key component for many state-of-the-art natural language representation models. A recent Transformer based model- BERT \citep{devlin2018bert} achieved state-of-the-art results on various natural language processing tasks, including GLUE, SQuAD v1.1, and SQuAD v2.0. This model however is computationally prohibitive and has a huge number of parameters. In this work we revisit the architecture choices of BERT in efforts to obtain a lighter model. We focus on reducing the number of parameters yet our methods can be applied towards o…
In this paper, the problem of head movement prediction for virtual reality videos is studied. In the considered model, a deep learning network is introduced to leverage position data as well as video frame content to predict future head movement. For optimizing data input into this neural network, data sample rate, reduced data, and long-period prediction length are also explored for this model. Simulation results show that the proposed approach yields 16.1\% improvement in terms of prediction accuracy compared to a baseline approach that relies only on the position data.
BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data
University of Georgia（佐治亚大学）；Department of Geography University of Georgia（佐治亚大学地理系）；College of Public Health University of Georgia（佐治亚大学公共卫生学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
End-to-End Transformer Acceleration Through Processing-in-Memory Architectures
Department of Electrical and Computer Engineering, University of Virginia（弗吉尼亚大学电气与计算机工程系）；Department of Electrical and Computer Engineering, Duke University（杜克大学电气与计算机工程系）
Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model understanding complex movement semantics. In this work, we present 9B-parameter transformer CogVideo, trained by inheriting a pretrained text-to-image model, CogView2. We also propose multi-frame-rate hierarchical training strategy to better align te…
A Foundation Model for Wearable Movement Data in Mental Health Research
Dartmouth College（达特茅斯学院）；National Institute of Diabetes and Digestive and Kidney Diseases（国家糖尿病、消化系统疾病和肾病研究所）；National Institutes of Health（美国国立卫生研究院）；Department of Computer Science at Dartmouth College（达特茅斯学院计算机科学系）
Deargen Inc.（迪尔根公司）；College of Computing at SungKyunKwan University（成均馆大学计算学院）；Department of Computer Science at Emory University（埃默里大学计算机科学系）
Generating a novel and optimized molecule with desired chemical properties is an essential part of the drug discovery process. Failure to meet one of the required properties can frequently lead to failure in a clinical test which is costly. In addition, optimizing these multiple properties is a challenging task because the optimization of one property is prone to changing other properties. In this paper, we pose this multi-property optimization problem as a sequence translation process and propose a new optimized molecule generator model based on the Transformer with two constraint networks: p…
Grasping is a fundamental robotic task needed for the deployment of household robots or furthering warehouse automation. However, few approaches are able to perform grasp detection in real time (frame rate). To this effect, we present Grasp Quality Spatial Transformer Network (GQ-STN), a one-shot grasp detection network. Being based on the Spatial Transformer Network (STN), it produces not only a grasp configuration, but also directly outputs a depth image centered at this configuration. By connecting our architecture to an externally-trained grasp robustness evaluation network, we can train e…
The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing tr…
