Search

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL. [ABSTRACT FROM AUTHOR]

This paper investigates the feasibility of novel data-driven deep learning (DL) models to predict the solution of Maxwell’s equations for low-frequency electromagnetic (EM) devices. With ground truth (empirical evidence) data being generated from a finite-element analysis solver, a deep convolutional neural network is trained in a supervised manner to learn a mapping for magnetic field distribution for topologies of different complexities of geometry, material, and excitation, including a simple coil, a transformer, and a permanent magnet motor. Preliminary experiments show DL model predictions in close agreement with the ground truth. A probabilistic model is introduced to improve the accuracy and to quantify the uncertainty in the prediction, based on Monte Carlo dropout. This paper establishes a basis for a fast and generalizable data-driven model used in the analysis, design, and optimization of EM devices. [ABSTRACT FROM AUTHOR]

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as “memory” for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a trained model is merely limited to either inference or better initialization towards a target task. In this paper, we go further and extract synthetic data by leveraging the learnt model parameters. We dub them Data Impressions, which act as proxy to the training data and can be used to realize a variety of tasks. These are useful in scenarios where only the pretrained models are available and the training data is not shared (e.g., due to privacy or sensitivity concerns). We show the applicability of data impressions in solving several computer vision tasks such as unsupervised domain adaptation, continual learning as well as knowledge distillation. We also study the adversarial robustness of lightweight models trained via knowledge distillation using these data impressions. Further, we demonstrate the efficacy of data impressions in generating data-free Universal Adversarial Perturbations (UAPs) with better fooling rates. Extensive experiments performed on benchmark datasets demonstrate competitive performance achieved using data impressions in absence of original training data. [ABSTRACT FROM AUTHOR]

As deep learning models are usually massive and complex, distributed learning is essential for increasing training efficiency. Moreover, in many real-world application scenarios like healthcare, distributed learning can also keep the data local and protect privacy. Recently, the asynchronous decentralized parallel stochastic gradient descent (ADPSGD) algorithm has been proposed and demonstrated to be an efficient and practical strategy where there is no central server, so that each computing node only communicates with its neighbors. Although no raw data will be transmitted across different local nodes, there is still a risk of information leak during the communication process for malicious participants to make attacks. In this paper, we present a differentially private version of asynchronous decentralized parallel SGD framework, or A(DP) $^2$ 2 SGD for short, which maintains communication efficiency of ADPSGD and prevents the inference from malicious participants. Specifically, Rényi differential privacy is used to provide tighter privacy analysis for our composite Gaussian mechanisms while the convergence rate is consistent with the non-private version. Theoretical analysis shows A(DP) $^2$ 2 SGD also converges at the optimal $\mathcal {O}(1/\sqrt{T})$ O (1 / T) rate as SGD. Empirically, A(DP) $^2$ 2 SGD achieves comparable model accuracy as the differentially private version of Synchronous SGD (SSGD) but runs much faster than SSGD in heterogeneous computing environments. [ABSTRACT FROM AUTHOR]

Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short text representations, making the previous clustering approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model for shot text clustering, wherein cluster-level attention is proposed to capture the correlations between text representations and cluster representations. Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model. To further ensure robust model training for short texts, we apply adversarial training to the unsupervised clustering setting, by injecting perturbations into the cluster representations. The model parameters and perturbations are optimized alternately through a minimax game. Extensive experiments on four real-world short text datasets demonstrate the superiority of the proposed model over several strong competitors, verifying that robust adversarial training yields substantial performance gains. [ABSTRACT FROM AUTHOR]

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-nearest neighbor dynamic time warping (1-NN DTW) and a fully convolutional network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples. [ABSTRACT FROM AUTHOR]

This paper presents a method to improve the traditional mixture of deformable part models (MDPM) method from the learning perspective. First, an object part configuration learning algorithm based on group sparsity constraint is introduced to automatically discover the object part number, size, and location. The algorithm imposes two additional regularization terms in addition to the standard hinge loss function. The first term focuses on automatic part selection and the second term focuses on automatic part placement. Second, this paper introduces an improved MDPM training framework. The framework applies a learned transformation to normalize the prediction score from each individual deformable part model (DPM) into a pseudo probability such that the partition of the entire object appearance feature space becomes less sensitive to the prior distributions of different DPMs. Finally, the two proposed improvements are combined and formulated under the expectation-maximization framework. We evaluate our method mainly using the PASCAL VOC2007 and VOC2010 detection benchmarks and show that the proposed learning algorithms could increase the detection mean AP score by 2.4% and 0.9%, respectively, on these two data sets when using the proposed part selection method and the training algorithm. We also present further in-depth analysis of the proposed algorithm in the experiments. [ABSTRACT FROM PUBLISHER]

Few-shot learning is an extremely challenging task in computer vision that has attracted increased research attention in recent years. However, most recent methods do not fully use the task’s information, and few of the seen samples result in large intraclass differences among the same classes. In this paper, we propose a novel task encoding with distribution calibration (TEDC) model for few-shot learning, which uses the relationships among the feature distributions to reduce intraclass differences. In the TEDC model, an integrated feature extraction module (IFEM) is proposed, which extracts the multiangle visual features of an image and fuses them to obtain more representative features. To effectively utilize the task information, a novel task encoding module (TEM) is proposed, which obtains the task features by fusing all the seen samples’ information and uses them to adjust all the samples’ features for more generalizable task-specific representations. We also propose a distribution calibration module (DCM) to reduce the bias between the distribution of the support features and the query features in the same class. Extensive experiments show that our proposed TEDC model achieves an excellent performance and outperforms the state-of-the-art methods on three widely used few-shot classification benchmarks, specifically miniImageNet, tieredImageNet and CUB-200-2011. [ABSTRACT FROM AUTHOR]

Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate the requirement of pixel-level dense annotations. Existing works mostly leverage the popular CNN classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we propose a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to improve the classification performance without a re-training burden. For each patch, we construct a multi-resolution image pyramid to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equip PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%). It greatly saves the computational resources and annotation efforts. The source code is available at: https://github.com/linjiatai/PDBL. [ABSTRACT FROM AUTHOR]

Deep learning (DL) techniques have shown promising performance for designing data-driven power system transient stability assessment (TSA) models. However, due to the deep structure of the DL, the resulting model is always a black-box and hard to explain, which hinders its practical adoption by the industry. This paper proposes an interpretable DL-based TSA model to balance the TSA accuracy and transparency. The proposed method combines the strong nonlinear modelling capability of a deep neural network and the interpretability of a decision tree (DT). Through regularizing DL-based model with the average DT path length in the training process, the proposed interpretable DL-based TSA method can visually explain the TSA decision-making process. Simulation results have shown that the proposed method can deliver highly accurate TSA results and interpretable TSA decision-making rules, which can be used for designing preventive control actions. [ABSTRACT FROM AUTHOR]

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant improvements in the performance of many NLP tasks. Though the Transformer encoder may effectively capture general information in its resulting representations, the backbone information, meaning the gist of the input text, is not specifically focused on. In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily. Our explicit text compression approaches use dedicated models to compress text, while our implicit text compression approach simply adds an additional module to the main model to handle text compression. We propose three ways of integration, namely backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the backbone information into Transformer-based models for various downstream tasks. Our evaluation on benchmark datasets shows that the proposed explicit and implicit text compression approaches improve results in comparison to strong baselines. We therefore conclude, when comparing the encodings to the baseline models, text compression helps the encoders to learn better language representations. [ABSTRACT FROM AUTHOR]

Signal classification problems arise in a wide variety of applications, and their demand is only expected to grow. In this paper, we focus on the wireless sensor network signal classification setting, where each sensor forwards quantized signals to a fusion center to be classified. Our primary goal is to train a decision function and quantizers across the sensors to maximize the classification performance in an online manner. Moreover, we are interested in sparse sensor selection using a marginalized weighted kernel approach to improve network resource efficiency by disabling less reliable sensors with minimal effect on classification performance. To achieve our goals, we develop a multi-sensor online kernel scalar quantization (MSOKSQ) learning strategy that operates on the sensor outputs at the fusion center. Our theoretical analysis reveals how the proposed algorithm affects the quantizers across the sensors. Additionally, we provide a convergence analysis of our online learning approach by studying its relationship to batch learning. We conduct numerical studies under different classification and sensor network settings which demonstrate the accuracy gains from optimizing different components of MSOKSQ and robustness to reduction in the number of sensors selected. [ABSTRACT FROM AUTHOR]

Effective non-parametric density estimation is a key challenge in high-dimensional multivariate data analysis. In this paper, we propose a novel approach that builds upon tensor factorization tools. Any multivariate density can be represented by its characteristic function, via the Fourier transform. If the sought density is compactly supported, then its characteristic function can be approximated, within controllable error, by a finite tensor of leading Fourier coefficients, whose size depends on the smoothness of the underlying density. This tensor can be naturally estimated from observed and possibly incomplete realizations of the random vector of interest, via sample averaging. In order to circumvent the curse of dimensionality, we introduce a low-rank model of this characteristic tensor, which significantly improves the density estimate especially for high-dimensional data and/or in the sample-starved regime. By virtue of uniqueness of low-rank tensor decomposition, under certain conditions, our method enables learning the true data-generating distribution. We demonstrate the very promising performance of the proposed method using several toy, measured, and image datasets. [ABSTRACT FROM AUTHOR]

We give an overview of recent developments in the modeling of radiowave propagation, based on machine learning (ML) algorithms. We identify the input and output specification and the architecture of the model as the main challenges associated with ML-driven propagation models. Relevant papers are discussed and categorized based on their approach to each of these challenges. Emphasis is given on presenting the prospects and open problems in this promising and rapidly evolving area. [ABSTRACT FROM AUTHOR]

The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. The key idea of TSM is to shift part of the channels along the temporal dimension, thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. TSM offers several unique advantages. First, TSM has high performance; it ranks the first on the Something-Something leaderboard upon submission. Second, TSM has high efficiency; it achieves a high frame rate of 74fps and 29fps for online video recognition on Jetson Nano and Galaxy Note8. Third, TSM has higher scalability compared to 3D networks, enabling large-scale Kinetics training on 1,536 GPUs in 15 minutes. Lastly, TSM enables action concepts learning, which 2D networks cannot model; we visualize the category attention map and find that spatial-temporal action detector emerges during the training of classification tasks. The code is publicly available at https://github.com/mit-han-lab/temporal-shift-module. [ABSTRACT FROM AUTHOR]

The peak-to-average power ratio (PAPR) reduction and linearization techniques are both effective methods to improve the efficiency of the transmitter in digital video broadcasting (DVB) systems. Traditional methods deploy the PAPR reduction model and the linearization model, respectively, without considering their mutual influence. Therefore, the joint optimizations of PAPR reduction and linearization techniques are proposed. However, these methods train the PAPR reduction model and the linearization model based on the time-division training method. It is difficult to meet the requirements of multiple objectives. To address this issue, this paper proposes a joint PAPR reduction and digital predistortion (DPD) method using the real-valued neural network (RVNN) for Orthogonal Frequency Division Multiplexing (OFDM) systems. The proposed method jointly trains the PAPR reduction function and the DPD function with multi-objective optimization, to achieve PAPR reduction and linearization simultaneously. Especially, this method unifies the PAPR reduction function and the DPD function into one model based on RVNN, and no extra processing is required at the receiver. Compared with the traditional methods, the experimental results show that the proposed method has superior performance in PAPR, adjacent channel power ratio (ACPR) and bit error rate (BER), while having lower computational complexity. [ABSTRACT FROM AUTHOR]

Image retargeting techniques adjust images into different sizes and have attracted much attention recently. Objective quality assessment (OQA) of image retargeting results is often desired to automatically select the best results. Existing OQA methods train a model using some benchmarks (e.g., RetargetMe), in which subjective scores evaluated by users are provided. Observing that it is challenging even for human subjects to give consistent scores for retargeting results of different source images (diff-source-results), in this paper we propose a learning-based OQA method that trains a General Regression Neural Network (GRNN) model based on relative scores—which preserve the ranking—of retargeting results of the same source image (same-source-results). In particular, we develop a novel training scheme with provable convergence that learns a common base scalar for same-source-results. With this source specific offset, our computed scores not only preserve the ranking of subjective scores for same-source-results, but also provide a reference to compare the diff-source-results. We train and evaluate our GRNN model using human preference data collected in RetargetMe. We further introduce a subjective benchmark to evaluate the generalizability of different OQA methods. Experimental results demonstrate that our method outperforms ten representative OQA methods in ranking prediction and has better generalizability to different datasets. [ABSTRACT FROM AUTHOR]

Cross-validation (CV) is a widely adopted approach for selecting the optimal model. However, the computation of empirical cross-validation error (CVE) has high complexity due to multiple times of learner training. In this paper, we develop a novel approximation theory of CVE and present an approximate approach to CV based on the Bouligand influence function (BIF) for kernel-based algorithms. We first represent the BIF and higher order BIFs in Taylor expansions, and approximate CV via the Taylor expansions. We then derive an upper bound of the discrepancy between the original and approximate CV. Furthermore, we provide a novel computing method to calculate the BIF for general distribution, and evaluate BIF criterion for sample distribution to approximate CV. The proposed approximate CV requires training on the full data set only once and is suitable for a wide variety of kernel-based algorithms. Experimental results demonstrate that the proposed approximate CV is sound and effective. [ABSTRACT FROM AUTHOR]

The inherent hysteresis property of piezoelectric actuator (PEA) brings challenges to its modeling and control. This paper proposes a model learning method that is suitable for both forward and inverse PEA models. The hysteresis property is learned based on least squares support vector machines (LS-SVMs). A larger dataset is used for training LS-SVM to guarantee a good generalization performance. Support vectors pruning is utilized to reduce the model complexity. The rate-dependent property of PEA is identified as a linear dynamic submodel. Moreover, a pointing control system with two dual-PEA-axis steering mirrors is developed, which can regulate the 4-degree-of-freedom pose of a laser beam. The coordinated control of four PEAs is realized based on the Jacobian matrix. The learned inverse PEA models are used for the feedforward compensation of each PEA’s nonlinearity. A series of experiments were conducted to evaluate the proposed method’s effectiveness. [ABSTRACT FROM AUTHOR]

Automatic target recognition (ATR) is an important part for many computer vision applications. Despite the extensive research which has been carried out in this area for many years, there is no ATR system which performs well on all applications. Recently, different object recognition frameworks have been proposed which yield a high performance in baseline databases. However, our experiments showed that they can fail in real-world scenarios, when dealing with a limited number of data samples. In this paper, we propose a new ATR system, based on deep convolutional neural network (DCNN), to detect the targets in forward looking infrared (FLIR) scenes and recognize their classes. In our proposed ATR framework, a fully convolutional network is trained to map the input FLIR imagery data to a fixed stride correspondingly-sized target score map. The potential targets are identified by applying a threshold on the target score map. Finally, the corresponding regions centered at these target points are fed to a DCNN to classify them into different target types while at the same time rejecting the false alarms. The proposed architecture achieves a significantly better performance in comparison with that of the state-of-the-art methods on two large FLIR image databases. [ABSTRACT FROM AUTHOR]

There is an increasingly higher number of mixed-signal circuits within microprocessors. A significant portion of them corresponds to high-speed input/output (HSIO) links. Post-silicon validation of HSIO links is critical to provide a release qualification decision. One of the major challenges in HSIO electrical validation is the physical layer (PHY) tuning process, where equalization techniques are typically used to cancel any undesired effect. Current industrial practices for PHY tuning in HSIO links are very time-consuming, since they require massive laboratory measurements. On the other hand, surrogate modeling techniques allow to develop an approximation of a system response within a design space of interest. In this paper, we analyze several surrogate modeling methods and design of experiments techniques to identify the best approach to efficiently optimize a receiver equalizer. We evaluate the models performance by comparing with actual measured responses on a real server HSIO link. We then perform a surrogate-based optimization on the best model to obtain the optimal PHY tuning settings of an HSIO link. Our methodology is validated by measuring the real functional eye diagram of the physical system using the optimal surrogate model solution. [ABSTRACT FROM AUTHOR]

Stochastic gradient descent (SGD) has become the method of choice for training highly complex and nonconvex models since it can not only recover good solutions to minimize training errors but also generalize well. Computational and statistical properties are separately studied to understand the behavior of SGD in the literature. However, there is a lacking study to jointly consider the computational and statistical properties in a nonconvex learning setting. In this paper, we develop novel learning rates of SGD for nonconvex learning by presenting high-probability bounds for both computational and statistical errors. We show that the complexity of SGD iterates grows in a controllable manner with respect to the iteration number, which sheds insights on how an implicit regularization can be achieved by tuning the number of passes to balance the computational and statistical errors. As a byproduct, we also slightly refine the existing studies on the uniform convergence of gradients by showing its connection to Rademacher chaos complexities. [ABSTRACT FROM AUTHOR]

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with general rectified linear activations, which constitute one of the most prevalent families of models for image classification and a host of other machine learning applications. We shed light on essential ingredients of these regularizations and re-interpret their functionality. Through the lens of our study, more principled and efficient regularizations can possibly be invented in the near future. [ABSTRACT FROM AUTHOR]

Automated machine learning (AutoML) has achieved remarkable progress on various tasks, which is attributed to its minimal involvement of manual feature and model designs. However, most of existing AutoML pipelines only touch parts of the full machine learning pipeline, e.g., neural architecture search or optimizer selection. This leaves potentially important components such as data cleaning and model ensemble out of the optimization, and still results in considerable human involvement and suboptimal performance. The main challenges lie in the huge search space assembling all possibilities over all components, as well as the generalization ability over different tasks like image, text, and tabular etc. In this paper, we present a first-of-its-kind fully AutoML pipeline, to comprehensively automate data preprocessing, feature engineering, model generation/selection/training and ensemble for an arbitrary dataset and evaluation metric. Our innovation lies in the comprehensive scope of a learning pipeline, with a novel “life-long” knowledge anchor design to fundamentally accelerate the search over the full search space. Such knowledge anchors record detailed information of pipelines and integrates them with an evolutionary algorithm for joint optimization across components. Experiments demonstrate that the result pipeline achieves state-of-the-art performance on multiple datasets and modalities. Specifically, the proposed framework was extensively evaluated in the NeurIPS 2019 AutoDL challenge, and won the only champion with a significant gap against other approaches, on all the image, video, speech, text and tabular tracks. [ABSTRACT FROM AUTHOR]

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search for each deployment specification of hardware or objective. This is a computationally impractical endeavor given the potentially large number of application scenarios. In this paper, we propose Neural Architecture Transfer (NAT) to overcome this limitation. NAT is designed to efficiently generate task-specific custom models that are competitive under multiple conflicting objectives. To realize this goal we learn task-specific supernets from which specialized subnets can be sampled without any additional training. The key to our approach is an integrated online transfer learning and many-objective evolutionary search procedure. A pre-trained supernet is iteratively adapted while simultaneously searching for task-specific subnets. We demonstrate the efficacy of NAT on 11 benchmark image classification tasks ranging from large-scale multi-class to small-scale fine-grained datasets. In all cases, including ImageNet, NATNets improve upon the state-of-the-art under mobile settings (≤ 600M Multiply-Adds). Surprisingly, small-scale fine-grained datasets benefit the most from NAT. At the same time, the architecture search and transfer is orders of magnitude more efficient than existing NAS methods. Overall, experimental evaluation indicates that, across diverse image classification tasks and computational objectives, NAT is an appreciably more effective alternative to conventional transfer learning of fine-tuning weights of an existing network architecture learned on standard datasets. Code is available at https://github.com/human-analysis/neural-architecture-transfer. [ABSTRACT FROM AUTHOR]

Multi-Task Learning attempts to explore and mine the sufficient information within multiple related tasks for the better solutions. However, the performance of the existing multi-task approaches would largely degenerate when dealing with the polluted data, i.e., outliers. In this paper, we propose a novel robust multi-task model by incorporating a flexible manifold constraint (FMC-MTL) and a robust loss. Specifically speaking, multi-task subspace is embedded with a relaxed and generalized Stiefel Manifold for considering point-wise correlation and preserving the data structure simultaneously. In addition, a robust loss function is developed to ensure the robustness to outliers by smoothly interpolating between ℓ2,1-norm and squared Frobenius norm. Equipped with an efficient algorithm, FMC-MTL serves as a robust solution to tackling the severely polluted data. Moreover, extensive experiments are conducted to verify the superiority of our model. Compared to the state-of-the-art multi-task models, the proposed FMC-MTL model demonstrates remarkable robustness to the contaminated data. [ABSTRACT FROM AUTHOR]

High-dimensional and sparse (HiDS) data with non-negativity constraints are commonly seen in industrial applications, such as recommender systems. They can be modeled into an HiDS matrix, from which non-negative latent factor analysis (NLFA) is highly effective in extracting useful features. Preforming NLFA on an HiDS matrix is ill-posed, desiring an effective regularization scheme for avoiding overfitting. Current models mostly adopt a standard ${L} _{2}$ scheme, which does not consider the imbalanced distribution of known data in an HiDS matrix. From this point of view, this paper proposes an instance-frequency-weighted regularization (IR) scheme for NLFA on HiDS data. It specifies the regularization effects on each latent factors with its relevant instance count, i.e., instance-frequency, which clearly describes the known data distribution of an HiDS matrix. By doing so, it achieves finely grained modeling of regularization effects. The experimental results on HiDS matrices from industrial applications demonstrate that compared with an ${L} _{2}$ scheme, an IR scheme enables a resultant model to achieve higher accuracy in missing data estimation of an HiDS matrix. [ABSTRACT FROM AUTHOR]

Accelerating the inference of CNNs is critical to their deployment in real-world applications. Among all pruning approaches, the methods of implementing a sparsity learning framework have shown effectiveness as they learn and prune the models in an end-to-end data-driven manner. However, these works impose the same sparsity regularization on all filters indiscriminately, which can hardly result in an optimal structure-sparse network. In this paper, we propose a Saliency-Adaptive Sparsity Learning (SASL) approach for further optimization. A novel and effective estimation of each filter, i.e., saliency, is designed, which is measured from two aspects: the importance for prediction performance and the consumed computational resources. During sparsity learning, the regularization strength is adjusted according to the saliency, so our optimized format can better preserve the prediction performance while zeroing out more computation-heavy filters. The calculation for saliency introduces minimum overhead to the training process, which means our SASL is very efficient. During the pruning phase, in order to optimize the proposed data-dependent criterion, a hard sample mining strategy is utilized, which shows higher effectiveness and efficiency. Extensive experiments demonstrate the superior performance of our method. Notably, on ILSVRC-2012 dataset, our approach can reduce 49.7% FLOPs of ResNet-50 with very negligible 0.39% top-1 and 0.05% top-5 accuracy degradation. [ABSTRACT FROM AUTHOR]

Dependency-aware jobs, such as the big data analytic workflows, are commonly executed on the cloud. They are compiled to directed acyclic graphs, with tasks linked in regarding the dependency. The cloud scheduler, which maintains a large number of resources, is responsible to execute tasks in parallel. To resolve the complex dependencies, Deep Reinforcement Learning (DRL) based schedulers are widely applied. However, we find that the DRL-based schedulers are vulnerable to the perturbations in the input jobs and may generate falsified decisions to benefit a particular job while delaying the others. By perturbation, we mean a slight adjustment to the job's node features or dependencies, while not changing its functionality. In this paper, we first explore the vulnerability of DRL-based schedulers to job perturbations without accessing the information of the DRL models used in the scheduler. We devise the black-box perturbation system, in which, a proxy model is trained to mimic the DRL-based scheduling policy. We show that the high-faith proxy model can help to craft effective perturbations. The DRL-based schedulers can be as high as 60% likely to be badly affected by the perturbations. Then, we investigate the solution to improve the robustness of DRL-based schedulers to such perturbations. We propose an adversarial training framework to force the neural model to adapt to the perturbation patterns during training so as to eliminate the potential damage during applications. Experiments show that the adversarial-trained scheduler is more robust, reducing the chance of being affected to 3-fold less and the potential bad effects halved. [ABSTRACT FROM AUTHOR]

Clinically oriented deep learning algorithms, combined with large-scale medical datasets, have significantly promoted computer-aided diagnosis. To address increasing ethical and privacy issues, Federated Learning (FL) adopts a distributed paradigm to collaboratively train models, rather than collecting samples from multiple institutions for centralized training. Despite intensive research on FL, two major challenges are still existing when applying FL in the real-world medical scenarios, including the performance degradation (i.e., retrogress) after each communication and the intractable class imbalance. Thus, in this paper, we propose a novel personalized FL framework to tackle these two problems. For the retrogress problem, we first devise a Progressive Fourier Aggregation (PFA) at the server side to gradually integrate parameters of client models in the frequency domain. Then, at the client side, we design a Deputy-Enhanced Transfer (DET) to smoothly transfer global knowledge to the personalized local model. For the class imbalance problem, we propose the Conjoint Prototype-Aligned (CPA) loss to facilitate the balanced optimization of the FL framework. Considering the inaccessibility of private local data to other participants in FL, the CPA loss calculates the global conjoint objective based on global imbalance, and then adjusts the client-side local training through the prototype-aligned refinement to eliminate the imbalance gap with such a balanced goal. Extensive experiments are performed on real-world dermoscopic and prostate MRI FL datasets. The experimental results demonstrate the advantages of our FL framework in real-world medical scenarios, by outperforming state-of-the-art FL methods with a large margin. The source code is available at https://github.com/CityU-AIM-Group/PRR-Imbalance https://github.com/CityU-AIM-Group/PRR-Imbalance. [ABSTRACT FROM AUTHOR]

The heterogeneity in recently published knowledge graph embedding models’ implementations, training, and evaluation has made fair and thorough comparisons difficult. To assess the reproducibility of previously published results, we re-implemented and evaluated 21 models in the PyKEEN software package. In this paper, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all, as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model’s performance and is not only determined by its architecture. We provide evidence that several architectures can obtain results competitive to the state of the art when configured carefully. We have made all code, experimental configurations, results, and analyses available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants collaboratively to train a global model without uploading raw data. Considering heterogeneous computing and communication capabilities of different participants, asynchronous FL can avoid the stragglers effect in synchronous FL and adapts to scenarios with vast participants. Both staleness and non-IID data in asynchronous FL would reduce the model utility. However, there exists an inherent contradiction between the solutions to the two problems. That is, mitigating the staleness requires to select less but consistent gradients while coping with non-IID data demands more comprehensive gradients. To address the dilemma, this paper proposes a two-stage weighted $K$ K asynchronous FL with adaptive learning rate (WKAFL). By selecting consistent gradients and adjusting learning rate adaptively, WKAFL utilizes stale gradients and mitigates the impact of non-IID data, which can achieve multifaceted enhancement in training speed, prediction accuracy and training stability. We also present the convergence analysis for WKAFL under the assumption of unbounded staleness to understand the impact of staleness and non-IID data. Experiments implemented on both benchmark and synthetic FL datasets show that WKAFL has better overall performance compared to existing algorithms. [ABSTRACT FROM AUTHOR]

Recently, angular margin-based methods have become the mainstream approach for unconstrained face recognition with remarkable success. However, robust face recognition still remains a challenge, as the face is subject to variations in pose, age, expression, occlusion, and illumination, especially in unconstrained scenarios. Since the training dataset are always collected in unconstrained scenarios, it is inevitable that there’re significant number of hard examples in the training process. In this paper, we design a hard example selection function to effectively identify hard examples in the training procedure with the supervision of angular margin-based losses. Furthermore, a novel Intra-class Hard Example Mining (IHEM) loss function is proposed, which penalizes the cosine distance between the hard examples and their class centers to enhance the discriminative power of face representations. To ensure high performance for face recognition, we combine the supervision of angular margin-based loss and IHEM loss for model training. Specifically, during the training procedure, the angular margin-based loss guarantees the power of feature discrimination for face recognition, while the IHEM loss further encourages the intra-class compactness of hard example. Extensive results demonstrate the superiority of our approach. [ABSTRACT FROM AUTHOR]

Intrinsic image decomposition is the task of mapping image to albedo and shading. Classical approaches derive methods from spatial models. The modern literature stresses evaluation, by comparing predictions to human judgements (“lighter”, “same as”, “darker”). The best modern intrinsic image methods train a map from image to albedo using images rendered from computer graphics models and example human judgements. This approach yields practical methods, but obtaining rendered images can be inconvenient. Furthermore, the approach cannot explain how a one could learn to recover intrinsic images without geometric, surface and illumination models, as people and animals appear to do. This paper describes a method that learns intrinsic image decomposition without seeing human annotations, rendered data, or ground truth data. Instead, the method relies on paradigms – spatial models of albedo and of shading. Rather than finding the “best” albedo and shading for an image via optimization, our approach trains a neural network on synthetic images. The synthetic images are constructed by multiplying albedos and shading fields sampled from our models. The network is subject to a novel smoothing procedure that ensures good behavior at short scales on real images. An averaging procedure ensures that reported albedo and shading are largely equivariant – different crops and scalings of an image will report the same albedo and shading at shared points. This averaging procedure controls long scale error. The standard evaluation for an intrinsic image method is a WHDR score. Our method achieves WHDR scores competitive with those of strong recent methods allowed to see training WHDR annotations, rendered data, and ground truth data. Our method produces albedo and shading maps with attractive qualitative properties – for example, albedo fields do not suppress wood grain and represent narrow grooves in surfaces well. Because our method is unsupervised, we can compute estimates of the test/train variance of WHDR scores; these are quite large, and suggest is unsafe to rely small differences in reported WHDR. [ABSTRACT FROM AUTHOR]

Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. As a representative one, the Bit-Flip-based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work of targeted BFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent vulnerable weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from ’Hen’ class into ’Goose’ class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy. Moreover, we successfully demonstrate our T-BFA attack in a real computer prototype system running DNN computation, with Ivy Bridge-based Intel i7 CPU and 8GB DDR3 memory. [ABSTRACT FROM AUTHOR]

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction. [ABSTRACT FROM AUTHOR]

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forecasting model's accuracy. To solve this problem, this paper proposes an integrated missing-data tolerant model for probabilistic PV power generation forecasting. Taking historical PV generations as input, this model is based on a recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead forecasting of the probability distribution of PV generation. The unobserved input data will be imputed recursively based on the model output at the previous time step. During the training process, the imputations and forecasting values are iteratively updated by the negative log-likelihood loss function. As a salient advantage, this method can deal with data missing scenarios at both offline and online stages. Numerical experiments are conducted on two one-year datasets from Australia and Singapore, respectively. Probabilistic forecasting for both large-scale and small-scale building-level PV power generation is tested at the time resolution of 15 mins. Testing results show the proposed method can achieve superior probabilistic prediction accuracy as well as strong robustness under various data missing scenarios, compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Training jobs of deep neural networks (DNNs) can be accelerated through distributed variants of stochastic gradient descent (SGD), where multiple nodes process training examples and exchange updates. The total throughput of the nodes depends not only on their computing power, but also on their networking speeds and coordination mechanism (synchronous or asynchronous, centralized or decentralized), since communication bottlenecks and stragglers can result in sublinear scaling when additional nodes are provisioned. In this paper, we propose two classes of performance models to predict throughput of distributed SGD: fine-grained models, representing many elementary computation/communication operations and their dependencies; and coarse-grained models, where SGD steps at each node are represented as a sequence of high-level phases without parallelism between computation and communication. Using a PyTorch implementation, real-world DNN models and different cloud environments, our experimental evaluation illustrates that, while fine-grained models are more accurate and can be easily adapted to new variants of distributed SGD, coarse-grained models can provide similarly accurate predictions when augmented with ad hoc heuristics, and their parameters can be estimated with profiling information that is easier to collect. [ABSTRACT FROM AUTHOR]

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness [ABSTRACT FROM AUTHOR]

With the integration of Artificial Intelligence (AI) and Internet of Things (IoT), the Federated Edge Learning (FEL), a promising computing framework is developing. However, there are still unsolved issues on communication efficiency and data security due to the huge models and unreliable transmission links. To address these issues, this paper proposes a novel federated edge learning system, called LightFed, where the edge nodes upload only vital partial local models, and successfully achieve lightweight communication and model aggregation. First, a novel model aggregation method Model Splitting and Splicing (MSS) and a Selective Parameter Transmission (SPT) scheme are proposed. By detecting the updating gradients of local parameters and filtering significant parameters, selective rotated transmission and efficient aggregation of local models are achieved. Second, a Training Filling Model (TFM) is proposed to infer the total data distribution of edge nodes, and train a filling model to mitigate the unbalanced training data without violating the data privacy of individual users. Moreover, a blockchain-powered confusion transmission mechanism is proposed for defending the attacks from external adversaries and protecting the model information. Finally, extensive experimental results demonstrate that our LightFed significantly outperforms the existing FEL systems in terms of communication efficiency and privacy security. [ABSTRACT FROM AUTHOR]

The accuracy of artificial intelligence (AI) models is crucial for connected and autonomous vehicles (CAVs). However, in reality, model training under less frequent weather faces the problem of insufficient sampling. Also, in the real world, weather, sunlight, etc., can only change with the speed of the real-time clock, so the traditional sampling process is very slow. Moreover, currently, collective learning, which can make up the limited experience and computing power of a single vehicle, is always introduced to cases where the data from participants have the same structure, wasting massive heterogeneous data from vehicles of different brands. Therefore, in this paper, we propose a quantum collective learning and many-to-many matching game-based scheme in the metaverse for CAVs. The environment is simulated in the metaverse, which has its own time clock system, thereby expanding sample size and speeding up the sampling process. And we quantify the quality of intelligence in collective learning from the perspective of feature diversity. It is the cornerstone of collective learning between heterogeneous vehicles, facilitating maximum utilization of data with different structures. Then, we formulate the distributed vehicles selection problem as a many-to-many matching game and use Gale–Shapely algorithm to solve it. Also, we formulate the spectrum resource allocation problem as a discrete Markov decision process (MDP) and adopt a quantum-inspired reinforcement learning (QRL) algorithm to find the optimal policy to achieve the high revenue of the system. In simulations, the performance of the proposed scheme is compared with existing methods. [ABSTRACT FROM AUTHOR]

Hyperdimensional computing (HDC) has emerged as an alternative lightweight learning solution to deep neural networks. A key characteristic of HDC is the great extent of parallelism that can facilitate hardware acceleration. However, previous hardware implementations of HDC seldom focus on GPU designs, which were also inefficient partly due to the complexity of accelerating HDC on GPUs. In this paper, we present OpenHD, a flexible and high-performance GPU-powered framework for automating the mapping of general HDC applications including classification and clustering to GPUs. OpenHD takes advantage of memory optimization strategies specialized for HDC, minimizing the access time to different memory subsystems, and removing redundant operations. We also propose a novel training method to enable data parallelism in HDC training. Our evaluation result shows that the proposed training rapidly achieves the target accuracy, reducing the required training epochs by 4×. With OpenHD, users can deploy GPU-accelerated HDC applications without domain expert knowledge. Compared to the state-of-the-art GPU-powered HDC implementation, our evaluation on NVIDIA Jetson TX2 shows that OpenHD is up to 10.5× and 314× faster for HDC-based classification and clustering, respectively. Compared with non-HDC classification and clustering on GPUs, OpenHD-based HDC is 11.7× and 53× faster at comparable accuracy. OpenHD is available at: https://github.com/UCSD-SEELab/openhd. [ABSTRACT FROM AUTHOR]