Search

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]

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]

How should affect be appropriately annotated and how should machine learning best be employed to map manifestations of affect to affect annotations? What is the use of ratings of affect for the study of affective computing and how should we treat them? These are the key questions this paper attempts to address by investigating the impact of dissimilar representations of annotated affect on the efficacy of affect modelling. In particular, we compare several different binary-class and pairwise preference representations for automatically learning from ratings of affect. The representations are compared and tested on three datasets: one synthetic dataset (testing “in vitro ”) and two affective datasets (testing “in vivo”). The synthetic dataset couples a number of attributes with generated rating values. The two affective datasets contain physiological and contextual user attributes, and speech attributes, respectively; these attributes are coupled with ratings of various affective and cognitive states. The main results of the paper suggest that ratings (when used) should be naturally transformed to ordinal (ranked) representations for obtaining more reliable and generalisable models of affect. The findings of this paper have a direct impact on affect annotation and modelling research but, most importantly, challenge the traditional state-of-practice in affective computing and psychometrics at large. [ABSTRACT FROM PUBLISHER]

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]

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables multiple clients to train a unified model without disclosing their private data. However, susceptibility to membership inference attacks (MIAs) arises due to the natural inclination of FL models to overfit on the training data during the training process, thereby enabling MIAs to exploit the subtle differences in the FL model’s parameters, activations, or predictions between the training and testing data to infer membership information. It is worth noting that most if not all existing MIAs against FL require access to the model’s internal information or modification of the training process, yielding them unlikely to be performed in practice. In this paper, we present with TEAR the first evidence that it is possible for an honest-but-curious federated client to perform MIA against an FL system, by exploring the Temporal Evolution of the Adversarial Robustness between the training and non-training data. We design a novel adversarial example generation method to quantify the target sample’s adversarial robustness, which can be utilized to obtain the membership features to train the inference model in a supervised manner. Extensive experiment results on five realistic datasets demonstrate that TEAR can achieve a strong inference performance compared with two existing MIAs, and is able to escape from the protection of two representative defenses. [ABSTRACT FROM AUTHOR]

There is growing interest in affective computing for the representation and prediction of emotions along ordinal scales. However, the term ordinal emotion label has been used to refer to both absolute notions such as low or high arousal, as well as relation notions such as arousal is higher at one instance compared to another. In this paper, we introduce the terminology absolute and relative ordinal labels to make this distinction clear and investigate both with a view to integrate them and exploit their complementary nature. We propose a Markovian framework referred to as Dynamic Ordinal Markov Model (DOMM) that makes use of both absolute and relative ordinal information, to improve speech based ordinal emotion prediction. Finally, the proposed framework is validated on two speech corpora commonly used in affective computing, the RECOLA and the IEMOCAP databases, across a range of system configurations. The results consistently indicate that integrating relative ordinal information improves absolute ordinal emotion prediction. [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]

Accurate and reliable load forecasting is essential for decision-making processes in the electric power industry. As the power industry transitions toward decarbonization, distributed energy systems, and integration of smart grid features, an increasing number of decision-making processes rely on uncertainty analysis of electric load. However, traditional point forecasting cannot address the uncertainties with only one forecasting value generated at each time step. As they are capable of representing uncertainties, probabilistic forecasts such as prediction intervals and quantile forecasts are preferred. Nevertheless, their practical application is limited partly due to the long training time of multiple probabilistic forecasting models. Traditional quantile regression neural network (QRNN) can train a single model for making quantile forecasts for multiple quantiles at one time. Whereas, the training cost is still unaffordable with large datasets. This paper proposes an improved QRNN (iQRNN) to address the issues of traditional QRNN, which incorporates popular techniques in deep learning areas. A case study on a publicly available dataset shows that not only can the proposed iQRNN generate remarkably superior quantile forecasts than state-of-the-art methods, but also the proposed iQRNN is more accurate, stable, and computationally efficient than traditional QRNN. [ABSTRACT FROM AUTHOR]

The cloud radio access network (C-RAN) is a promising paradigm to meet the stringent requirements of the fifth generation (5G) wireless systems. Meanwhile, the wireless traffic prediction is a key enabler for C-RANs to improve both the spectrum efficiency and energy efficiency through load-aware network managements. This paper proposes a scalable Gaussian process (GP) framework as a promising solution to achieve large-scale wireless traffic prediction in a cost-efficient manner. Our contribution is three-fold. First, to the best of our knowledge, this paper is the first to empower GP regression with the alternating direction method of multipliers (ADMM) for parallel hyper-parameter optimization in the training phase, where such a scalable training framework well balances the local estimation in baseband units (BBUs) and information consensus among BBUs in a principled way for large-scale executions. Second, in the prediction phase, we fuse local predictions obtained from the BBUs via a cross-validation-based optimal strategy, which demonstrates itself to be reliable and robust for general regression tasks. Moreover, such a cross-validation-based optimal fusion strategy is built upon a well acknowledged probabilistic model to retain the valuable closed-form GP inference properties. Third, we propose a C-RAN-based scalable wireless prediction architecture, where the prediction accuracy and the time consumption can be balanced by tuning the number of the BBUs according to the real-time system demands. The experimental results show that our proposed scalable GP model can outperform the state-of-the-art approaches considerably, in terms of wireless traffic prediction performance. [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]

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]

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]

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]

Dynamic routing networks, aimed at finding the best routing paths in the networks, have achieved significant improvements to neural networks in terms of accuracy and efficiency. In this paper, we see dynamic routing networks in a fresh light, formulating a routing method as a mapping from a sample space to a routing space. From the perspective of space mapping, prevalent methods of dynamic routing did not take into account how routing paths would be distributed in the routing space. Thus, we propose a novel method, termed CoDiNet, to model the relationship between a sample space and a routing space by regularizing the distribution of routing paths with the properties of consistency and diversity. In principle, the routing paths for the self-supervised similar samples should be closely distributed in the routing space.Moreover, we design a customizable dynamic routing module, which can strike a balance between accuracy and efficiency. When deployed upon ResNet models, our method achieves higher performance and effectively reduces average computational cost on four widely used datasets. [ABSTRACT FROM AUTHOR]

Wide models such as generalized linear models and factorization-based models have been extensively used in various predictive applications, e.g., recommendation, CTR prediction, and image recognition. Due to the memory bounded property of the models, the performance improvement on CPU is reaching the limitation. GPU is known to have many computation units and high memory bandwidth, and becomes a promising platform for training machine learning models. However, the GPU training for the wide models is far from optimal due to the sparsity and irregularity in wide models. The existing GPU-based wide models are even slower than the ones using CPU. The classical training schema of the wide models does not optimized for the GPU architecture, which suffers from large amount of random memory accesses and redundant read/write of intermediate values. In this paper, we propose an efficient GPU-training framework for the large-scale wide models, named cuWide. To fully benefit from the memory hierarchy of GPU, cuWide applies a new flow-based schema for training, which leverages the spatial and temporal locality of wide models to drastically reduce the amount of communication with GPU global memory. To do so, we adopt a bigraph computation model to efficiently realize the flow-based schema and exploit three flexible interfaces for programming. Further, we use the 2D partition of mini-batch (in sample and feature dimensions) with proposed graph abstraction to optimize GPU memory access for sparse data, and apply several spatial-temporal caching mechanisms (importance-based model caching and cross-stage accumulation caching mechanisms) to achieve a high performance kernel. To efficiently implement cuWide, we also propose several GPU-oriented optimizations, including feature-oriented data layout to enhance the data locality, replication mechanism to reduce update conflicts in shared memory, and multi-stream scheduling to overlap data transferring and kernel computing. We show that cuWide can be up to more than 20× faster than the state-of-the-art GPU solutions and multi-core CPU solutions. [ABSTRACT FROM AUTHOR]

Accurate short-term traffic flow prediction plays an important role in the field of modern Intelligent Transportation Systems. Since various uncontrollable factors (e.g. weather, traffic jams or accidents), collected traffic data inevitably contain outliers. This makes it challenge to achieve satisfactory results for traffic flow prediction. Least Squares Twin Support Vector Regression (LSTSVR) has been shown to provide a powerful potential in nonlinear prediction problems. This is especially true when using appropriate heuristic algorithms to determine the parameters of nonlinear LSTSVR. In view of this, a novel LSTSVR model based on the robust $\text{L}_{2,\mathrm {p}}$ -norm ($0< p\le 2$) distance is proposed to alleviate the negative effect of traffic data with outliers, called PLSTSVR. An iterative algorithm is designed to solve the optimization problem of PLSTSVR, which has great potential for solving other relevant optimization problems. To search the parameters of constructed PLSTSVR, this paper constructs two traffic flow prediction models based on PLSTSVR and heuristic algorithms (Fruit Fly Optimization Algorithm and Particle Swarm Optimization), called PLSTSVR-FOA and PLSTSVR-PSO. Extensive experiments demonstrate that the constructed models are more effective and robust than other competing models in various experimental settings. [ABSTRACT FROM AUTHOR]

Summarization systems for various applications, such as opinion mining, online news services, and answering questions, have attracted increasing attention in recent years. These tasks are complicated, and a classic representation using bag-of-words does not adequately meet the comprehensive needs of applications that rely on sentence extraction. In this paper, we focus on representing sentences as continuous vectors as a basis for measuring relevance between user needs and candidate sentences in source documents. Embedding models based on distributed vector representations are often used in the summarization community because, through cosine similarity, they simplify sentence relevance when comparing two sentences or a sentence/query and a document. However, the vector-based embedding models do not typically account for the salience of a sentence, and this is a very necessary part of document summarization. To incorporate sentence salience, we developed a model, called CCTSenEmb, that learns latent discriminative Gaussian topics in the embedding space and extended the new framework by seamlessly incorporating both topic and sentence embedding into one summarization system. To facilitate the semantic coherence between sentences in the framework of prediction-based tasks for sentence embedding, the CCTSenEmb further considers the associations between neighboring sentences. As a result, this novel sentence embedding framework combines sentence representations, word-based content, and topic assignments to predict the representation of the next sentence. A series of experiments with the DUC datasets validate CCTSenEmb's efficacy in document summarization in a query-focused extraction-based setting and an unsupervised ILP-based setting. [ABSTRACT FROM AUTHOR]

In recent years, data has become the new oil that fuels various machine learning (ML) applications. Just as the oil refining, providing data to an ML model is a product of massive costs and expertise efforts. However, how to protect the intellectual property (IP) of the training data in ML remains largely open. In this paper, we present MeFA, a novel framework for detecting training data IP embezzlement via Membership Fingerprint Authentication, which is able to determine whether a suspect ML model is trained on the to be protected target data or not. The key observation is that a part of data has a similar influence on the prediction behavior of different ML models. On this basis, MeFA leverages membership inference techniques to extract these data as the fingerprints of the target data and constructs an authentication model to verify the data’s ownership by identifying the obtained membership fingerprints. MeFA has several salient features. It does not assume any knowledge of the suspect model except for its black-box prediction API, through which we can merely get the prediction output of a given input, and also does not require any modification to the dataset or the training process, since it takes advantage of the inherent membership property of the data. As a by-product, MeFA can also serve as a post-protection to verify the ownership of ML models, without modifying the training process of the model. Extensive experiments on three realistic datasets and seven types of ML models validate the effectiveness of MeFA, and demonstrate that it is also robust to scenarios when the training data is partially used or preprocessed with representative membership inference defenses. [ABSTRACT FROM AUTHOR]

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate “weak” models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks. [ABSTRACT FROM AUTHOR]

We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor maps the learned representations to quality scores in a No-Reference (NR) setting. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models, even without any additional fine-tuning of the CNN backbone. The learned representations are highly robust and generalize well across images afflicted by either synthetic or authentic distortions. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets. The implementations used in this paper are available at https://github.com/pavancm/CONTRIQUE. [ABSTRACT FROM AUTHOR]

Recent studies have pointed out that many well-developed Visual Question Answering (VQA) models are heavily affected by the language prior problem. It refers to making predictions based on the co-occurrence pattern between textual questions and answers instead of reasoning upon visual contents. To tackle this problem, most existing methods focus on strengthening the visual feature learning capability to reduce this text shortcut influence on model decisions. However, few efforts have been devoted to analyzing its inherent cause and providing an explicit interpretation. It thus lacks a good guidance for the research community to move forward in a purposeful way, resulting in model construction perplexity towards overcoming this non-trivial problem. In this paper, we propose to interpret the language prior problem in VQA from a class-imbalance view. Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers from the same question type is distinctly exhibited during the late training phase. It explicitly reveals why the VQA model tends to produce a frequent yet obviously wrong answer, to a given question whose right answer is sparse in the training set. Based upon this observation, we further propose a novel loss re-scaling approach to assign different weights to each answer according to the training data statistics for estimating the final loss. We apply our approach into six strong baselines and the experimental results on two VQA-CP benchmark datasets evidently demonstrate its effectiveness. In addition, we also justify the validity of the class imbalance interpretation scheme on other computer vision tasks, such as face recognition and image classification. [ABSTRACT FROM AUTHOR]

In this paper, the content popularity prediction problem in fog radio access networks (F-RANs) is investigated. In order to obtain accurate prediction with low complexity, we propose a novel context-aware popularity prediction policy based on federated learning (FL). Firstly, user preference learning is applied by considering that users prefer to request the contents they are interested in. Then, users’ context information is utilized to cluster users efficiently by adaptive context space partitioning. After that, we formulate a popularity prediction optimization problem to learn the local model parameters by using the stochastic variance reduced gradient (SVRG) algorithm. Finally, FL based model integration is proposed to learn the global popularity prediction model based on local models using the distributed approximate Newton (DANE) algorithm with SVRG. Our proposed popularity prediction policy not only can predict content popularity accurately, but also can significantly reduce computational complexity. Moreover, we theoretically analyze the convergence bound of our proposed FL based model integration algorithm. Simulation results show that our proposed policy increases the cache hit rate by up to 21.5 % compared to existing policies. [ABSTRACT FROM AUTHOR]

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We first define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions. [ABSTRACT FROM AUTHOR]

Actuated by the growing attention to personal healthcare and the pandemic, the popularity of E-health is proliferating. Nowadays, enhancement on medical diagnosis via machine learning models has been highly effective in many aspects of e-health analytics. Nevertheless, in the classic cloud-based/centralized e-health paradigms, all the data will be centrally stored on the server to facilitate model training, which inevitably incurs privacy concerns and high time delay. Distributed solutions like Decentralized Stochastic Gradient Descent (D-SGD) are proposed to provide safe and timely diagnostic results based on personal devices. However, methods like D-SGD are subject to the gradient vanishing issue and usually proceed slowly at the early training stage, thereby impeding the effectiveness and efficiency of training. In addition, existing methods are prone to learning models that are biased towards users with dense data, compromising the fairness when providing E-health analytics for minority groups. In this paper, we propose a Decentralized Block Coordinate Descent (D-BCD) learning framework that can better optimize deep neural network-based models distributed on decentralized devices for E-health analytics. As a gradient-free optimization method, Block Coordinate Descent (BCD) mitigates the gradient vanishing issue and converges faster at the early stage compared with the conventional gradient-based optimization. To overcome the potential data scarcity issues for users’ local data, we propose similarity-based model aggregation that allows each on-device model to leverage knowledge from similar neighbor models, so as to achieve both personalization and high accuracy for the learned models. Benchmarking experiments on three real-world datasets illustrate the effectiveness and practicality of our proposed D-BCD, where additional simulation study showcases the strong applicability of D-BCD in real-life E-health scenarios. [ABSTRACT FROM AUTHOR]

When implementing unfamiliar programming tasks, developers commonly search code examples and learn usage patterns of APIs from the code examples or reuse them by copy-pasting and modifying. For providing high-quality code examples, previous studies present several methods to recommend code snippets mainly based on information retrieval. In this paper, to provide better recommendation results, we propose ROSF, Recommending code Snippets with multi-aspect Features, a novel method combining both information retrieval and supervised learning. In our method, we recommend Top-K code snippets for a given free-form query based on two stages, i.e., coarse-grained searching and fine-grained re-ranking. First, we generate a code snippet candidate set by searching a code snippet corpus using an information retrieval method. Second, we predict probability values of the code snippets for different relevance scores in the candidate set by the learned prediction model from a training set, re-rank these candidate code snippets according to the probability values, and recommend the final results to developers. We conduct several experiments to evaluate our method in a large-scale corpus containing 921,713 real-world code snippets. The results show that ROSF is an effective method for code snippets recommendation and outperforms the-state-of-the-art methods by 20-41percent in Precision and 13-33 percent in NDCG. [ABSTRACT FROM AUTHOR]

Since heavy flows account for a significant fraction of network traffic, being able to predict heavy flows has benefited many network management applications for mitigating link congestion, scheduling of network capacity, exposing network attacks and so on. Existing machine learning based predictors are largely implemented on the control plane of Software Defined Networking (SDN) paradigm. As a result, frequent communication between the control and data planes can cause unnecessary overhead and additional delay in decision making. In this paper, we present pHeavy, a machine learning based scheme for predicting heavy flows directly on the programmable data plane, thus eliminating network overhead and latency to SDN controller. Considering the scarce memory and limited computation capability in the programmable data plane, pHeavy includes a packet processing pipeline which deploys pre-trained decision tree models for in-network prediction. We have implemented pHeavy in both bmv2 software switch and P4 hardware switch (i.e., Barefoot Tofino). Evaluation results demonstrate that pHeavy has achieved 85% and 98% accuracy after receiving the first 5 and 20 packets of a flow respectively, while being able to reduce the size of decision tree by 5.4x on average. More importantly, pHeavy can predict heavy flows at line rate on the P4 hardware switch. [ABSTRACT FROM AUTHOR]

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of membership privacy risks against machine learning models, this paper presents a comprehensive study towards demystifying membership inference attacks from two complimentary perspectives. First, we provide a generalized formulation of the development of a black-box membership inference attack model. Second, we characterize the importance of model choice on model vulnerability through a systematic evaluation of a variety of machine learning models and model combinations using multiple datasets. Through formal analysis and empirical evidence from extensive experimentation, we characterize under what conditions a model may be vulnerable to such black-box membership inference attacks. We show that membership inference vulnerability is data-driven and corresponding attack models are largely transferable. Though different model types display different vulnerabilities to membership inference, so do different datasets. Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning exposes vulnerabilities to membership inference risks when the adversary is a participant. We also discuss countermeasure and mitigation strategies. [ABSTRACT FROM AUTHOR]

Predicting the future trajectories of surrounding agents has become an crucial problem to be solved for the safety of autonomous vehicles. Recent studies based on Long Short Term Memory (LSTM) networks have shown powerful abilities to model social interactions. However, many of these approaches focus on spatial interactions of the neighborhood agents but ignore temporal interactions that accompany spatial interactions. In this paper, we propose a Hierarchical Spatio-Temporal Attention architecture (HSTA), which activates the utilization of spatial interactions with different weights, and jointly considers the temporal interactions across time steps of all agents. More specially, the graph attention mechanism (GAT) is presented to capture spatial interactions, the multi-head attention mechanism (MHA) is conducted to encode temporal correlations of interactions and a state gated fusion (SGF) layer is used to integrate spatial and temporal interactions. We evaluate our proposed method against baselines on both pedestrian and vehicle datasets. The results show that our model is effective and achieves state-of-the-art achievements. [ABSTRACT FROM AUTHOR]

Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]

In visual tracking, how to effectively model the target appearance using limited prior information remains an open problem. In this paper, we leverage an ensemble of diverse models to learn manifold representations for robust object tracking. The proposed ensemble framework includes a shared backbone network for efficient feature extraction and multiple head networks for independent predictions. Trained by the shared data within an identical structure, the mutually correlated head models heavily hinder the potential of ensemble learning. To shrink the representational overlaps among multiple models while encouraging the diversity of individual predictions, we propose the model diversity and response diversity regularization terms during training. By fusing these distinctive prediction results via a fusion module, the tracking variance caused by the distractor objects can be largely restrained. Our whole framework is end-to-end trained in a data-driven manner, avoiding the heuristic designs of multiple base models and fusion strategies. The proposed method achieves state-of-the-art results on seven challenging benchmarks while operating in real-time. [ABSTRACT FROM AUTHOR]

Due to the advanced capabilities of the Internet of Vehicles (IoV) components such as vehicles, Roadside Units (RSUs) and smart devices as well as the increasing amount of data generated, Federated Learning (FL) becomes a promising tool given that it enables privacy-preserving machine learning that can be implemented in the IoV. However, the performance of the FL suffers from the failure of communication links and missing nodes, especially when continuous exchanges of model parameters are required. Therefore, we propose the use of Unmanned Aerial Vehicles (UAVs) as wireless relays to facilitate the communications between the IoV components and the FL server and thus improving the accuracy of the FL. However, a single UAV may not have sufficient resources to provide services for all iterations of the FL process. In this paper, we present a joint auction-coalition formation framework to solve the allocation of UAV coalitions to groups of IoV components. Specifically, the coalition formation game is formulated to maximize the sum of individual profits of the UAVs. The joint auction-coalition formation algorithm is proposed to achieve a stable partition of UAV coalitions in which an auction scheme is applied to solve the allocation of UAV coalitions. The auction scheme is designed to take into account the preferences of IoV components over heterogeneous UAVs. The simulation results show that the grand coalition, where all UAVs join a single coalition, is not always stable due to the profit-maximizing behavior of the UAVs. In addition, we show that as the cooperation cost of the UAVs increases, the UAVs prefer to support the IoV components independently and not to form any coalition. [ABSTRACT FROM AUTHOR]

Given a spatial raster framework with explanatory feature layers, a spatial contextual layer (e.g., a potential field), as well as a set of training samples with class labels, the spatial prediction problem aims to learn a model that can predict a class layer. The problem is important in societal applications such as flood extent mapping for disaster response and national water forecasting, but is challenging due to the noise, obstacles, and heterogeneity in feature maps, implicit spatial dependency between locations based on the contextual layer (e.g., gradient directions on a potential field), and the large number of sample locations. Existing work often assumes undirected spatial dependency, or directed dependency with a total order, and thus cannot reflect complex directed dependency with a partial order. In contrast, we recently proposed geographical hidden Markov tree, a probabilistic graphical model that generalizes the common hidden Markov model from a one-dimensional sequence to a two-dimensional map. Partial order class dependency is incorporated in the hidden class layer with a reverse tree structure. We also investigated computational algorithms for reverse tree construction, model parameter learning and class inference. This paper extends our recent model with overlaying class nodes between observation nodes and underlying hidden class nodes. The additional overlaying class layer makes the model more robust to large scale feature obstacles. We also proposed corresponding learning and inference methods. Extensive evaluations on real world datasets show that our models outperform multiple baselines in flood mapping applications, our algorithms are scalable on large data sizes, and the proposed extension enhances classification performance. [ABSTRACT FROM AUTHOR]

A key problem in postsilicon validation is to identify a small set of traceable signals that are effective for debug during silicon execution. Structural analysis used by traditional signal selection techniques leads to a poor restoration quality. In contrast, simulation-based selection techniques provide superior restorability but incur significant computation overhead. In this paper, we propose an efficient signal selection technique using machine learning to take advantage of simulation-based signal selection while significantly reducing the simulation overhead. The basic idea is to train a machine learning framework with a few simulation runs and utilize its effective prediction capability (instead of expensive simulation) to identify beneficial trace signals. Specifically, our approach uses: (1) bounded mock simulations to generate training vectors for the machine learning technique and (2) a compound search-space exploration approach to identify the most profitable signals. Experimental results indicate that our approach can improve restorability by up to 143.1% (29.2% on average) while maintaining or improving runtime compared with the state-of-the-art signal selection techniques. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a new model called Latent Mixture of Discriminative Experts which can automatically learn the temporal relationship between different modalities. Since, we train separate experts for each modality, LMDE is capable of improving the prediction performance even with limited amount of data. For model interpretation, we present a sparse feature ranking algorithm that exploits L1 regularization. An empirical evaluation is provided on the task of listener backchannel prediction (i.e., head nod). We introduce a new error evaluation metric called User-adaptive Prediction Accuracy that takes into account the difference in people's backchannel responses. Our results confirm the importance of combining five types of multimodal features: lexical, syntactic structure, part-of-speech, visual and prosody. Latent Mixture of Discriminative Experts model outperforms previous approaches. [ABSTRACT FROM PUBLISHER]

Visuo-spatial neglect (often simply referred to as “neglect”) is a complex poststroke medical syndrome which may be assessed by means of a series of drawing-based tests. Based on a novel analysis of a test battery formed from established pencil-and-paper tests, the aim of this study is to develop an automated assessment system which enables objectivity, repeatability, and diagnostic capability in the scoring process. Furthermore, the novel assessment system encapsulates temporal sequence and other “dynamic” information inherent in the drawing process. Several approaches are introduced in this paper and the results compared. The optimal model is shown to produce significant agreement with the score for drawing-related components of the Rivermead Behavioural Inattention Test, the widely accepted standardised clinical test for the diagnosis of neglect, and, more importantly, to encapsulate data to enable an enhanced test resolution with a reduction in battery size. [ABSTRACT FROM PUBLISHER]

Advances in biomedical sensors and mobile communication technologies have fostered the rapid growth of mobile health (mHealth) applications in the past years. Users generate a high volume of biomedical data during health monitoring, which can be used by the mHealth server for training predictive models for disease diagnosis and treatment. However, the biomedical sensing data raise serious privacy concerns because they reveal sensitive information such as health status and lifestyles of the sensed subjects. This paper proposes and experimentally studies a scheme that keeps the training samples private while enabling accurate construction of predictive models. We specifically consider logistic regression models which are widely used for predicting dichotomous outcomes in healthcare, and decompose the logistic regression problem into small subproblems over two types of distributed sensing data, i.e., horizontally partitioned data and vertically partitioned data. The subproblems are solved using individual private data, and thus mHealth users can keep their private data locally and only upload (encrypted) intermediate results to the mHealth server for model training. Experimental results based on real datasets show that our scheme is highly efficient and scalable to a large number of mHealth users. [ABSTRACT FROM PUBLISHER]

Defect detection and classification in semiconductor wafers has received an increasing attention from both industry and academia alike. Wafer defects are a serious problem that could cause massive losses to the companies’ yield. The defects occur as a result of a lengthy and complex fabrication process involving hundreds of stages, and they can create unique patterns. If these patterns were to be identified and classified correctly, then the root of the fabrication problem can be recognized and eventually resolved. Machine learning (ML) techniques have been widely accepted and are well suited for such classification-/identification problems. However, none of the existing ML model’s performance exceeds 96% in identification accuracy for such tasks. In this paper, we develop a state-of-the-art classifying algorithm using multiple ML techniques, relying on a general-regression-network-based consensus learning model along with a powerful randomization technique. We compare our proposed method with the widely used ML models in terms of model accuracy, stability, and time complexity. Our method has proved to be more accurate and stable as compared to any of the existing algorithms reported in the literature, achieving its accuracy of 99.8%, stability of 1.128, and TBM of 15.8 s. [ABSTRACT FROM AUTHOR]

The increasing penetration of stochastic photovoltaic (PV) generation in electric power systems poses significant challenges to system operators. To ensure reliable operation of power systems, accurate forecasting of PV power production is essential. In this paper, we propose a novel multitime-scale data-driven forecast model to improve the accuracy of short-term PV power production. This model leverages both spatial and temporal correlations among neighboring solar sites, and is shown to have improved performance compared to the conventional persistence (PSS) model. The tradeoff between computation cost and improved forecast quality is studied using real datasets from PV sites in California and Colorado. [ABSTRACT FROM PUBLISHER]

Advances in sensing, computation, storage, and actuation technologies have entered cyber-physical systems (CPSs) into the smart era where complex control applications requiring high performance are supported. Neural networks (NNs) models are proposed as a predictive model to be used in model predictive control (MPC) applications. However, the ability to efficiently exploit resource hungry NNs in embedded resource-bound settings is a major challenge. In this paper, we propose priority neuron network (PNN), a resource-aware NNs model that can be reconfigured into smaller subnetworks at runtime. This approach enables a tradeoff between the model’s computation time and accuracy based on available resources. The PNN model is memory efficient since it stores only one set of parameters to account for various subnetwork sizes. We propose a training algorithm that applies regularization techniques to constrain the activation value of neurons and assigns a priority to each one. We consider the neuron’s ordinal number as our priority criteria in that the priority of the neuron is inversely proportional to its ordinal number in the layer. This imposes a relatively sorted order on the activation values. We conduct experiments to employ our PNN as the predictive model of a vehicle in MPC for path tracking. To corroborate the effectiveness of our proposed methodology, we compare it with two state-of-the-art methods for resource-aware NN design. Compared to state-of-the-art work, our approach can cut down the training time by 87% and reduce the memory storage by 75% while achieving similar accuracy. Moreover, we decrease the computation overhead for the model reduction process that searches for neurons below a threshold, from $ {O(n)}$ to $ {O}$ (log $ {n}$). [ABSTRACT FROM AUTHOR]

Computational models of interactive narrative offer significant potential for creating educational game experiences that are procedurally tailored to individual players and support learning. A key challenge posed by interactive narrative is devising effective director agent models that dynamically sequence story events according to players' actions and needs. In this paper, we describe a supervised machine-learning framework to model director agent strategies in an educational interactive narrative Crystal Island. Findings from two studies with human participants are reported. The first study utilized a Wizard-of-Oz paradigm where human “wizards” directed participants through Crystal Island's mystery storyline by dynamically controlling narrative events in the game environment. Interaction logs yielded training data for machine learning the conditional probabilities of a dynamic Bayesian network (DBN) model of the human wizards' directorial actions. Results indicate that the DBN model achieved significantly higher precision and recall than naive Bayes and bigram model techniques. In the second study, the DBN director agent model was incorporated into the runtime version of Crystal Island, and its impact on students' narrative-centered learning experiences was investigated. Results indicate that machine-learning director agent strategies from human demonstrations yield models that positively shape players' narrative-centered learning and problem-solving experiences. [ABSTRACT FROM PUBLISHER]

Cross-subject EEG emotion recognition suffers a major setback due to high inter-subject variability in emotional responses. Many prior studies have endeavored to alleviate the inter-subject discrepancies of EEG feature distributions, ignoring the variable EEG connectivity and prediction deviation caused by individual differences, which may cause poor generalization to the unseen subject. This article proposes a graph domain disentanglement network (GDDN) to generalize EEG emotion recognition across subjects in terms of EEG connectivity, representation, and prediction. More specifically, a graph domain disentanglement module is proposed to extract common-specific characteristics on both EEG graph connectivity and graph representation, enabling a more comprehensive network transferability to the unseen individual. Meanwhile, to strengthen stable emotion prediction capability, a domain-adaptive classifier aggregation module is developed to facilitate adaptive emotional prediction for the unseen individual conditioned on the domain weights of the input individuals. Finally, an auxiliary supervision module is imposed to alleviate the domain discrepancy and reduce information loss during the disentanglement learning. Extensive experiments on three public EEG emotion datasets, i.e., SEED, SEED-IV, and MPED, validate the superior generalizability of GDDN compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Multi-party conversation modeling plays a vital role in emotion recognition in conversation (ERC). Aside from the intra- and inter-speaker dependencies between different speakers, the difficulty also lies in the fact that each conversation may contain several to many utterances that compose a long text sequence. In this article, we present two approaches to effective multi-party conversation modeling. First, to encode long sequences and capture long-range dependency between utterances, we introduce a dialog-oriented language model, DialogXL, with enhanced memory to store longer conversation sequences and dialog-aware self-attention to deal with multi-party dependencies. Second, we present a directed acyclic neural network, namely DAG-ERC, to encode the utterances with a directed acyclic graph (DAG) to better capture the intrinsic structure within a conversation. DAG-ERC combines the advantages of recurrent models and graph models and provides a more intuitive way to model information flow between sequential utterances. Extensive experiments are conducted on four ERC benchmarks with state-of-the-art models employed for comparison, and empirical results demonstrate the superiority of the two models in multi-party conversation modeling. [ABSTRACT FROM AUTHOR]