Training time budget and size of the dataset are among the factors affecting the performance of a Deep Neural Network (DNN). This paper shows that Neural Architecture Search (NAS), Hyper Parameters Optimization (HPO), and Data Augmentation help DNNs perform much better while these two factors are limited. However, searching for an optimal architecture and the best hyperparameter values besides a good combination of data augmentation techniques under low resources requires many experiments. We present our approach to achieving such a goal in three steps: reducing training epoch time by compressing the model while maintaining the performance compared to the original model, preventing model overfitting when the dataset is small, and performing the hyperparameter tuning. We used NOMAD, which is a blackbox optimization software based on a derivative-free algorithm to do NAS and HPO. Our work achieved an accuracy of 86.0 % on a tiny subset of Mini-ImageNet at the ICLR 2021 Hardware Aware Efficient Training (HAET) Challenge and won second place in the competition. The competition results can be found at haet2021.github.io/challenge and our source code can be found at github.com/DouniaLakhmiri/ICLR\_HAET2021.
In most practical settings and theoretical analyses, one assumes that a model can be trained until convergence. However, the growing complexity of machine learning datasets and models may violate such assumptions. Indeed, current approaches for hyper-parameter tuning and neural architecture search tend to be limited by practical resource constraints. Therefore, we introduce a formal setting for studying training under the non-asymptotic, resource-constrained regime, i.e., budgeted training. We analyze the following problem: "given a dataset, algorithm, and fixed resource budget, what is the be…
In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have underutilized computational resources. This observation motivates a lot of research topics, e.g. network pruning, architecture search, etc. As models with higher computational costs (e.g. more parameters or more computations) usually have better performances, we study the problem of improving the resource utilization of neural networks so that their potentials ca…
Nanjing University of Science and Technology（南京理工大学）；National University of Singapore（新加坡国立大学）；University of California, Irvine（加州大学欧文分校）
Recently many research efforts have been devoted to image annotation by leveraging on the associated tags/keywords of web images as training labels. A key issue to resolve is the relatively low accuracy of the tags. In this paper, we propose a novel semi-automatic framework to construct a more accurate and effective training set from these web media resources for each label that we want to learn. Experiments conducted on a real-world dataset demonstrate that the constructed training set can result in higher accuracy for image annotation.
Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources
Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam（信息科技学院，科学大学，胡志明市，越南）；Vietnam National University, Ho Chi Minh City, Vietnam（越南国家大学，胡志明市，越南）
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)（Vicomtech基金会，巴斯克研究与技术联盟）；Institute of Smart Cities, Public University of Navarre（纳瓦拉公立大学智慧城市研究所）
In the recent years, cybersecurity has gained high relevance, converting the detection of attacks or intrusions into a key task. In fact, a small breach in a system, application, or network, can cause huge damage for the companies. However, when this attack detection encounters the Artificial Intelligence paradigm, it can be addressed using high-quality classifiers which often need high resource demands in terms of computation or memory usage. This situation has a high impact when the attack classifiers need to be used with limited resourced devices or without overloading the performance of th…
Deep learning (DL) workflows demand an ever-increasing budget of compute and energy in order to achieve outsized gains. Neural architecture searches, hyperparameter sweeps, and rapid prototyping consume immense resources that can prevent resource-constrained researchers from experimenting with large models and carry considerable environmental impact. As such, it becomes essential to understand how different deep neural networks (DNNs) and training leverage increasing compute and energy resources -- especially specialized computationally-intensive models across different domains and application…
Nanjing University of Science and Technology（南京理工大学）
Resource constraints, e.g. limited product inventory or financial strength, may affect consumers' choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics. Accordingly, we propose an interest-behavior multiplicative network to predict the user's future interaction based on dynamic connections between users and items. To…
Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）
Recent advances in deep reinforcement learning (DRL) have largely promoted the performance of adaptive traffic signal control (ATSC). Nevertheless, regarding the implementation, most works are cumbersome in terms of storage and computation. This hinders their deployment on scenarios where resources are limited. In this work, we propose TinyLight, the first DRL-based ATSC model that is designed for devices with extremely limited resources. TinyLight first constructs a super-graph to associate a rich set of candidate features with a group of light-weighted network blocks. Then, to diminish the m…
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
Institute of High Performance Computing, A*STAR（高性能计算研究院（新加坡科技研究局））
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are designed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are triv…
Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our ana…
National University of Computer and Emerging Sciences (NUCES-FAST)（国立计算机与新兴科学大学）
Deep learning algorithms have made many breakthroughs and have various applications in real life. Computational resources become a bottleneck as the data and complexity of the deep learning pipeline increases. In this paper, we propose optimized deep learning pipelines in multiple aspects of training including time and memory. OpTorch is a machine learning library designed to overcome weaknesses in existing implementations of neural network training. OpTorch provides features to train complex neural networks with limited computational resources. OpTorch achieved the same accuracy as existing l…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；University of Southampton（南安普顿大学）
A central problem in business concerns the optimal allocation of limited resources to a set of available tasks, where the payoff of these tasks is inherently uncertain. In credit card fraud detection, for instance, a bank can only assign a small subset of transactions to their fraud investigations team. Typically, such problems are solved using a classification framework, where the focus is on predicting task outcomes given a set of characteristics. Resources are then allocated to the tasks that are predicted to be the most likely to succeed. However, we argue that using classification to addr…
National Tsing Hua University（台湾清华大学）；IBM Research（IBM研究院）
Current transfer learning methods are mainly based on finetuning a pretrained model with target-domain data. Motivated by the techniques from adversarial machine learning (ML) that are capable of manipulating the model prediction via data perturbations, in this paper we propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box ML model (e.g., a prediction API or a proprietary software) for solving different ML tasks, especially in the scenario with scarce data and constrained resources. The rationale lies in exploiting high-performance but un…
University of California, San Diego（加州大学圣迭戈分校）；University of Maryland（马里兰大学）
We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription. After supervised fine-tuning of our pre-trained encoder representations for low-resource document transcription on two languages, (1) a heterogeneous set of handwritten Islamicate manuscript images and (2) early modern English printed documents, we show a meaningful improvement in recognition accuracy over the same supervised model trained from scratch with as few as 30 line image transcriptions for training. Our masked languag…
Microsoft Research（微软研究院）；Beihang University（北京航空航天大学）
Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages. In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference…
Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University（中山大学电子与通信工程学院（深圳校区））；Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China（电子科技大学智能网络与通信中心）
Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial static training set, model performance and reliability suffer from changes of acquisition characteristics as data and targets may become inconsistent. Continual learning can help to adapt models to the changing environment by training on a continuous data stream. However, continual manual expert labelling of medical imaging requires substantial effort. Thus, ways…
Our goal is to design architectures that retain the groundbreaking performance of Convolutional Neural Networks (CNNs) for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost p…
We study the role of an essential hyper-parameter that governs the training of Transformers for neural machine translation in a low-resource setting: the batch size. Using theoretical insights and experimental evidence, we argue against the widespread belief that batch size should be set as large as allowed by the memory of the GPUs. We show that in a low-resource setting, a smaller batch size leads to higher scores in a shorter training time, and argue that this is due to better regularization of the gradients during training.
Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Data Science and Analytics Thrust, HKUST (GZ)（香港科技大学（广州）数据科学与分析学域）；The Chinese University of Hong Kong（香港中文大学）
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）；Capital Medical University（首都医科大学）；Tsinghua University（清华大学）
Huge computational costs brought by convolution and batch normalization (BN) have caused great challenges for the online training and corresponding applications of deep neural networks (DNNs), especially in resource-limited devices. Existing works only focus on the convolution or BN acceleration and no solution can alleviate both problems with satisfactory performance. Online training has gradually become a trend in resource-limited devices like mobile phones while there is still no complete technical scheme with acceptable model performance, processing speed, and computational cost. In this r…
Resource-Limited Automated Ki67 Index Estimation in Breast Cancer
Università degli Studi di Milano（米兰大学）；European Commission, Joint Research Centre (JRC)（欧盟委员会联合研究中心）；Humanitas University（人道大学）；IRCCS Humanitas Clinical and Research Hospital（IRCCS人道临床与研究医院）；CINI National Laboratory in Artificial Intelligence and Intelligent Systems（CINI人工智能与智能系统国家实验室）
Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser's output when applied to unlabeled data, and integrates these models with the base parser t…
University of Miami Libraries（迈阿密大学图书馆）；Stanford Libraries（斯坦福大学图书馆）；British Library（大英图书馆）；Smithsonian（史密森学会）
We take a snapshot of current resources available for teaching and learning AI with a focus on the Galleries, Libraries, Archives and Museums (GLAM) community. The review was carried out in 2021 and 2022. The review provides an overview of material we identified as being relevant, offers a description of this material and makes recommendations for future work in this area.
Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient subgraph-level training via resource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level.…
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
In this paper we propose strategies for estimating performance of a classifier when labels cannot be obtained for the whole test set. The number of test instances which can be labeled is very small compared to the whole test data size. The goal then is to obtain a precise estimate of classifier performance using as little labeling resource as possible. Specifically, we try to answer, how to select a subset of the large test set for labeling such that the performance of a classifier estimated on this subset is as close as possible to the one on the whole test set. We propose strategies based on…
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noi…
Blind Network Revenue Management and Bandits with Knapsacks under Limited Switches
Department of Civil and Environmental Engineering, Operations Research Center, and Institute for Data, Systems, and Society, Massachusetts Institute of Technology（土木与环境工程系、运筹中心及数据、系统与社会研究所，麻省理工学院）；Department of Industrial and Enterprise Systems Engineering, Grainger College of Engineering, University of Illinois（工业与企业系统工程系、格拉inger工程学院，伊利诺伊大学）；Questrom School of Business, Boston University（乔斯特罗商学院，波士顿大学）
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training perf…
Many decisions involve choosing an uncertain course of actions in deep and wide decision trees, as when we plan to visit an exotic country for vacation. In these cases, exhaustive search for the best sequence of actions is not tractable due to the large number of possibilities and limited time or computational resources available to make the decision. Therefore, planning agents need to balance breadth (exploring many actions at each level of the tree) and depth (exploring many levels in the tree) to allocate optimally their finite search capacity. We provide efficient analytical solutions and …
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；School of Software & Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University（软件学院及山东大学-东北大学人工智能研究联合中心（C-FAIR））
Qualcomm Technologies Netherlands B.V.（高通荷兰技术有限公司）；African Institute for Mathematical Sciences（非洲数学科学研究所）
Thanks to their improved data efficiency, equivariant neural networks have gained increased interest in the deep learning community. They have been successfully applied in the medical domain where symmetries in the data can be effectively exploited to build more accurate and robust models. To be able to reach a much larger body of patients, mobile, on-device implementations of deep learning solutions have been developed for medical applications. However, equivariant models are commonly implemented using large and computationally expensive architectures, not suitable to run on mobile devices. I…
Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier's performance when trained on this data. We propose a noise layer that is added to a neural network architecture. This allows modeling the noise and train on a combination of clean and noisy data. We show that in a low-resource NER task we can improve performance by up to 35% by using additional, n…
