Power consumption is a major obstacle in the deployment of deep neural networks (DNNs) on end devices. Existing approaches for reducing power consumption rely on quite general principles, including avoidance of multiplication operations and aggressive quantization of weights and activations. However, these methods do not take into account the precise power consumed by each module in the network, and are therefore not optimal. In this paper we develop accurate power consumption models for all arithmetic operations in the DNN, under various working conditions. We reveal several important factors that have been overlooked to date. Based on our analysis, we present PANN (power-aware neural network), a simple approach for approximating any full-precision network by a low-power fixed-precision variant. Our method can be applied to a pre-trained network, and can also be used during training to achieve improved performance. In contrast to previous methods, PANN incurs only a minor degradation in accuracy w.r.t. the full-precision version of the network, even when working at the power-budget of a 2-bit quantized variant. In addition, our scheme enables to seamlessly traverse the power-accuracy trade-off at deployment time, which is a major advantage over existing quantization methods that are constrained to specific bit widths.
This work utilizes a MobileNetV2 Convolutional Neural Network (CNN) for fast, mobile detection of satellites, and rejection of stars, in cluttered unresolved space imagery. First, a custom database is created using imagery from a synthetic satellite image program and labeled with bounding boxes over satellites for "satellite-positive" images. The CNN is then trained on this database and the inference is validated by checking the accuracy of the model on an external dataset constructed of real telescope imagery. In doing so, the trained CNN provides a method of rapid satellite identification fo…
Humans rely less on spurious correlations and trivial cues, such as texture, compared to deep neural networks which lead to better generalization and robustness. It can be attributed to the prior knowledge or the high-level cognitive inductive bias present in the brain. Therefore, introducing meaningful inductive bias to neural networks can help learn more generic and high-level representations and alleviate some of the shortcomings. We propose InBiaseD to distill inductive bias and bring shape-awareness to the neural networks. Our method includes a bias alignment objective that enforces the n…
High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction
School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆邮电大学计算机科学与技术学院）；Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences（中国科学院重庆绿色智能技术研究院）；College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）
Shanghai Jiao Tong University（上海交通大学）；National Institute of Information and Communications Technology（日本国立信息通信研究机构）
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first retrieve a diversity of images from a shared cross-modal embedding space, which is pre-trained on a large-scale of text-image pairs. Then, the texts and images are respectively encoded by transformer encoder and convolutional neural network. The two sequences of representations are further fused by a simple and effective attention layer. The architecture can be …
Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing
Deakin University（迪肯大学）；The University of Melbourne（墨尔本大学）；University of Cambridge（剑桥大学）；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Islamic University of Technology（伊斯兰技术大学）；University of Alberta（阿尔伯塔大学）；H2O.ai
Since the dawn of mankind's introduction to powered flights, there have been multiple incidents which can be attributed to aircraft stalls. Most modern-day aircraft are equipped with advanced warning systems to warn the pilots about a potential stall, so that pilots may adopt the necessary recovery measures. But these warnings often have a short window before the aircraft actually enters a stall and require the pilots to act promptly to prevent it. In this paper, we propose a deep learning based approach to predict an Impending stall, well in advance, even before the stall-warning is triggered…
Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Automation and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学自动化与智能制造学院）；Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, Southern University of Science and Technology（广东省全驱动系统控制理论与技术重点实验室，南方科技大学）；Pengcheng Laboratory（鹏城实验室）
The prevalence of social media has made information sharing possible across the globe. The downside, unfortunately, is the wide spread of misinformation. Methods applied in most previous rumor classifiers give an equal weight, or attention, to words in the microblog, and do not take the context beyond microblog contents into account; therefore, the accuracy becomes plateaued. In this research, we propose an ensemble neural architecture to detect rumor on Twitter. The architecture incorporates word attention and context from the author to enhance the classification performance. In particular, t…
Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost. This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). By formalizing the uncertainty quantification as a minimax learning problem, we first identify input distance awareness, i.e., the model's ability to quantify the distance of a testing exa…
Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. It becomes important for ML systems in critical applications to accurately quantify its predictive uncertainty and screen out these anomalous inputs. However, existing OoD detection approaches are prone to errors and even sometimes assign higher likelihoods to OoD samples. Unlike standard learning tasks, there is currently no well established guiding principle for designing OoD detection architectures that can accurately quantify…
Rochester Institute of Technology（罗切斯特理工学院）；Pennsylvania State University（宾夕法尼亚州立大学）
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural generative coding, a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. Specifically, we develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. We demonstrate on several simple control p…
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers. Recent emerged quantization technique has been applied to inference of deep neural networks for fast and efficient execution. However, directly applying quantization in training can cause significant accuracy loss, thus remaining an open challenge.
Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the…
We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and only a small proportion of important features in a higher precision to preserve accuracy. The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss. Our experiments indicate that PG achieves excellent results on CNNs, including statically compressed mobile-friendly networks such as ShuffleNet. Compared to the sta…
Brown University（布朗大学）；Ben-Gurion University（本-古里安大学）
Quantized neural networks (QNNs) are among the main approaches for deploying deep neural networks on low resource edge devices. Training QNNs using different levels of precision throughout the network (dynamic quantization) typically achieves superior trade-offs between performance and computational load. However, optimizing the different precision levels of QNNs can be complicated, as the values of the bit allocations are discrete and difficult to differentiate for. Also, adequately accounting for the dependencies between the bit allocation of different layers is not straight-forward. To meet…
East China Normal University（华东师范大学）；Southern University of Science and Technology（南方科技大学）
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of singe-objective combinatorial optimization (SOCO) problems and train attention models based on a single-step and deterministic greedy rollout. However, inappropriate decomposition and undesirable short-sighted behaviors of previous methods tend to induce a decline in diversity. To address the above limitation, we design a Context-aware Diversity Enhancement algorithm named CDE, …
Eindhoven University of Technology（埃因霍温理工大学）；NXP Semiconductors（恩智浦半导体）
Bayesian Optimization Mixed-Precision Neural Architecture Search (BOMP-NAS) is an approach to quantization-aware neural architecture search (QA-NAS) that leverages both Bayesian optimization (BO) and mixed-precision quantization (MP) to efficiently search for compact, high performance deep neural networks. The results show that integrating quantization-aware fine-tuning (QAFT) into the NAS loop is a necessary step to find networks that perform well under low-precision quantization: integrating it allows a model size reduction of nearly 50\% on the CIFAR-10 dataset. BOMP-NAS is able to find neu…
Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the exact quantization scheme. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. These approaches cannot lead to an optimal quantization scheme efficiently. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization …
We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a neural network into individual bitlayers and accumulates them using fast 1-bit operations while maintaining activations in full precision. PrecisionBatching not only facilitates quantized inference at low bitwidths (< 8 bits) without the need for retraining/recalibration, but also 1) enables traditional hardware platforms the ability to realize inference speedups…
Though deep learning has pushed the boundaries of classification forward, in recent years hints of the limits of standard classification have begun to emerge. Problems such as fooling, adding new classes over time, and the need to retrain learning models only for small changes to the original problem all point to a potential shortcoming in the classic classification regime, where a comprehensive a priori knowledge of the possible classes or concepts is critical. Without such knowledge, classifiers misjudge the limits of their knowledge and overgeneralization therefore becomes a serious obstacl…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Jilin University（吉林大学）
Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which combines the advantages of fast convolution and quantization techniques. By embedding linear quantization operations into the Winograd-domain, the fast convolution can be performed efficiently under low-precision computation on graphics processing units. We test neural network models with LANCE on representative image classification datasets, including SVHN,…
Australian National University (ANU)（澳大利亚国立大学）；DATA61, CSIRO（联邦科学与工业研究组织DATA61）；KFUPM（法赫德国王石油和矿产大学）；SDAIA-KFUPM JRCAI（沙特数据和人工智能治理局-法赫德国王石油和矿产大学联合人工智能研究中心）；OPPO US Research Center（OPPO美国研发中心）；POSTECH（浦项科技大学）；Curtin University（科廷大学）；Obuda University Hungary（匈牙利奥布达大学）
We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed with high-precision weights while quantized low-precision weights and activations are used in the forward pass to calculate the loss function for training. Thus, the gradient descent becomes suboptimal, and accuracy loss follows. In order to reduce the mismatch in the forward and backward passes, we utilize mean squared quantization error (MSQE) regularizat…
Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple and efficient. The proposed method succeeds in training NNs with 16-bit fixed-point numbers and provides faster convergence and higher classification accuracy than both CSR and deterministic rounding-to-the-nearest method.
Graph neural networks (GNNs) are emerging machine learning models on graphs. Permutation-equivariance and proximity-awareness are two important properties highly desirable for GNNs. Both properties are needed to tackle some challenging graph problems, such as finding communities and leaders. In this paper, we first analytically show that the existing GNNs, mostly based on the message-passing mechanism, cannot simultaneously preserve the two properties. Then, we propose Stochastic Message Passing (SMP) model, a general and simple GNN to maintain both proximity-awareness and permutation-equivari…
Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to account for the different sensitivities of different filters and is suboptimal. Mixed-precision networks address this problem, by tuning the bit-width to individual filter requirements. In this work, the problem of optimal mixed-precision network search (MPS) is considered. To circumvent its difficulties of discrete search space and combinatorial optimization, a …
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is a powerful tool to address the growing computational cost of such applications, and yields significant compression over full-precision networks. However, quantization can result in substantial loss of performance for complex image classification tasks. To address this, we propose a Principal Component Analysis (PCA) driven methodology to identify the important layers of a binary network, and design mixed-precision n…
NVIDIA（英伟达）；University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高等研究院）
Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to adversarial attacks. However, typical implementations of low precision DNNs use uniform precision across all layers of the network. In this work, we explore whether a heterogeneous allocation of precision across a network leads to improved performance, and introduce a learning scheme where a DNN stochastically explores multiple precision configurations through lea…
Carnegie Mellon Uni.（卡内基梅隆大学）；Michigan State Uni.（密歇根州立大学）；Snap Inc.（Snap公司）
Message Passing Neural Networks (MPNNs) are a common type of Graph Neural Network (GNN), in which each node's representation is computed recursively by aggregating representations (messages) from its immediate neighbors akin to a star-shaped pattern. MPNNs are appealing for being efficient and scalable, how-ever their expressiveness is upper-bounded by the 1st-order Weisfeiler-Lehman isomorphism test (1-WL). In response, prior works propose highly expressive models at the cost of scalability and sometimes generalization performance. Our work stands between these two regimes: we introduce a gen…
Department of Electrical and Computer Engineering（电气与计算机工程系）；University of Toronto（多伦多大学）；Toronto, ON, Canada（加拿大安大略省多伦多市）
Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We present a novel dynamic precision scaling (DPS) scheme. Using stochastic fixed-point rounding, a quantization-error based scaling scheme, and dynamic bit-widths during training, we achieve 98.8% test accuracy on the MNIST dataset using an average bit-width of just 16 bits for weights and 14 bits for activations, compared to the standard 32-bit floating point v…
In this paper, we evaluate training of deep recurrent neural networks with half-precision floats. We implement a distributed, data-parallel, synchronous training algorithm by integrating TensorFlow and CUDA-aware MPI to enable execution across multiple GPU nodes and making use of high-speed interconnects. We introduce a learning rate schedule facilitating neural network convergence at up to $O(100)$ workers. Strong scaling tests performed on clusters of NVIDIA Pascal P100 GPUs show linear runtime and logarithmic communication time scaling for both single and mixed precision training modes. Per…
Institute of Computer Science, University of St.Gallen (HSG)（圣加仑大学（HSG）计算机科学研究所）
The commitment to single-precision floating-point arithmetic is widespread in the deep learning community. To evaluate whether this commitment is justified, the influence of computing precision (single and double precision) on the optimization performance of the Conjugate Gradient (CG) method (a second-order optimization algorithm) and RMSprop (a first-order algorithm) has been investigated. Tests of neural networks with one to five fully connected hidden layers and moderate or strong nonlinearity with up to 4 million network parameters have been optimized for Mean Square Error (MSE). The trai…
University of Delaware（特拉华大学）；Texas A&M University（德克萨斯A&M大学）
The objective of this study is to create and test a hybrid deep learning model, FastGRNN-FCN (Fast, Accurate, Stable and Tiny Gated Recurrent Neural Network-Fully Convolutional Network), for urban flood prediction and situation awareness using channel network sensors data. The study used Harris County, Texas as the testbed, and obtained channel sensor data from three historical flood events (e.g., 2016 Tax Day Flood, 2016 Memorial Day flood, and 2017 Hurricane Harvey Flood) for training and validating the hybrid deep learning model. The flood data are divided into a multivariate time series an…
Stanford University（斯坦福大学）；Intel AI Lab（英特尔人工智能实验室）
Training with larger number of parameters while keeping fast iterations is an increasingly adopted strategy and trend for developing better performing Deep Neural Network (DNN) models. This necessitates increased memory footprint and computational requirements for training. Here we introduce a novel methodology for training deep neural networks using 8-bit floating point (FP8) numbers. Reduced bit precision allows for a larger effective memory and increased computational speed. We name this method Shifted and Squeezed FP8 (S2FP8). We show that, unlike previous 8-bit precision training methods,…
Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；UPS（图卢兹第三大学）
We explore the influence of precision of the data and the algorithm for the simulation of chaotic dynamics by neural networks techniques. For this purpose, we simulate the Lorenz system with different precisions using three different neural network techniques adapted to time series, namely reservoir computing (using ESN), LSTM and TCN, for both short and long time predictions, and assess their efficiency and accuracy. Our results show that the ESN network is better at predicting accurately the dynamics of the system, and that in all cases the precision of the algorithm is more important than t…
Analog electronic and optical computing exhibit tremendous advantages over digital computing for accelerating deep learning when operations are executed at low precision. In this work, we derive a relationship between analog precision, which is limited by noise, and digital bit precision. We propose extending analog computing architectures to support varying levels of precision by repeating operations and averaging the result, decreasing the impact of noise. Such architectures enable programmable tradeoffs between precision and other desirable performance metrics such as energy efficiency or t…
University of California, Irvine（加州大学欧文分校）；Rain Neuromorphics Inc（Rain Neuromorphics公司）
Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that preserves accuracy is not easily found, especially with the abundance of models, datasets, and quantization techniques that creates an enormous search space. In order to tackle this difficulty, a body of literature has emerged recently, and several frameworks that achieved promising accuracy results have been proposed. In this paper, we start by summarizing t…
Reduced numerical precision is a common technique to reduce computational cost in many Deep Neural Networks (DNNs). While it has been observed that DNNs are resilient to small errors and noise, no general result exists that is capable of predicting a given DNN system architecture's sensitivity to reduced precision. In this project, we emulate arbitrary bit-width using a specified floating-point representation with a truncation method, which is applied to the neural network after each batch. We explore the impact of several model parameters on the network's training accuracy and show results on…
Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ logarithmic quantization in lieu of fixed-point quantization. However, we find bias terms are less amenable to log quantization but note they comprise a tiny fraction of the model, so we leave them uncompressed. We also propose to use an error-feedback mechanism during retraining, to preserve the compressed model as a stale gradient. We empirically show that NMT mode…
SenseTime Research（商汤科技研究院）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）；Harvard University（哈佛大学）
Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to improve the overall performance. However, it is challenging to find the optimal bitwidth (i.e., precision) for weights and activations of each layer efficiently. Meanwhile, it is yet unclear how to perform convolution for weights and activations of different precision efficiently on generic hardware platforms. To resolve these two issues, in this paper, we first p…
