Search

Video Object Segmentation (VOS) methods have made many breakthroughs with the help of the continuous development and advancement of deep learning. However, the deep learning model is vulnerable to malicious adversarial attacks, which mislead the model to make wrong decisions by adding adversarial perturbation that humans cannot perceive to the input image. Threats to deep learning models remind us that video object segmentation methods are also vulnerable to attacks, thereby threatening their security. Therefore, we study adversarial attacks on the VOS task to better identify the vulnerabilities of the VOS method, which in turn provides an opportunity to improve its robustness. In this paper, we propose an attention-guided adversarial attack method, which uses spatial attention blocks to capture features with global dependencies to construct correlations between consecutive video frames, and performs multipath aggregation to effectively integrate spatial-temporal perturbation, thereby guiding the deconvolution network to generate adversarial examples with strong attack capability. Specifically, the class loss function is designed to enable the deconvolution network to better activate noise in other regions and suppress the activation related to the object class based on the enhanced feature map of the object class. At the same time, attentional feature loss is designed to enhance the transferability against attack. The experimental results on the DAVIS dataset show that the proposed attention-guided adversarial attack method can significantly reduce the segmentation accuracy of OSVOS, and the J&F mean on DAVIS 2016 can reach 73.6% drop rate. The generated adversarial examples are also highly transferable to other video object segmentation models. [ABSTRACT FROM AUTHOR]

Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021, focusing on models from traditional models to deep learning. We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification. We then discuss each of these categories in detail, dealing with both the technical developments and benchmark datasets that support tests of predictions. A comprehensive comparison between different techniques, as well as identifying the pros and cons of various evaluation metrics are also provided in this survey. Finally, we conclude by summarizing key implications, future research directions, and the challenges facing the research area. [ABSTRACT FROM AUTHOR]

Similar trajectory search is a crucial task that facilitates many downstream spatial data analytic applications. Despite its importance, many of the current literature focus solely on the trajectory's spatial similarity while neglecting the temporal information. Additionally, the few papers that use both the spatial and temporal features based their approach on a traditional point-to-point comparison. These methods model the importance of the spatial and temporal aspect of the data with only a single, pre-defined balancing factor for all trajectories, even though the relative spatial and temporal balance can change from trajectory to trajectory. In this article, we propose the first spatio-temporal, deep-representation-learning-based approach to similar trajectory search. Experiments show that utilizing both features offers significant improvements over existing point-to-point comparison and deep-representation-learning approach. We also show that our deep neural network approach is faster and performs more consistently compared to the point-to-point comparison approaches. [ABSTRACT FROM AUTHOR]

L2 regularization for weights in neural networks is widely used as a standard training trick. In addition to weights, the use of batch normalization involves an additional trainable parameter γ, which acts as a scaling factor. However, L2 regularization for γ remains an undiscussed mystery and is applied in different ways depending on the library and practitioner. In this article, we study whether L2 regularization for γ is valid. To explore this issue, we consider two approaches: (1) variance control to make the residual network behave like an identity mapping and (2) stable optimization through the improvement of effective learning rate. Through two analyses, we specify the desirable and undesirable γ to apply L2 regularization and propose four guidelines for managing them. In several experiments, we observed that applying L2 regularization to applicable γ increased 1% to 4% classification accuracy, whereas applying L2 regularization to inapplicable γ decreased 1% to 3% classification accuracy, which is consistent with our four guidelines. Our proposed guidelines were further validated through various tasks and architectures, including variants of residual networks and transformers. [ABSTRACT FROM AUTHOR]

Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the single-cell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this article, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional deep learning models. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets where the labeling effort is entrusted to the clients. While most existing FL approaches assume high-quality labels are readily available on users' devices, in reality, label noise can naturally occur in FL and is closely related to clients' characteristics. Due to scarcity of available data and significant label noise variations among clients in FL, existing state-of-the-art centralized approaches exhibit unsatisfactory performance, whereas prior FL studies rely on excessive on-device computational schemes or additional clean data available on the server. We propose FedLN, a framework to deal with label noise across different FL training stages, namely FL initialization, on-device model training, and server model aggregation, able to accommodate the diverse computational capabilities of devices in an FL system. Specifically, FedLN computes per-client noise level estimation in a single federated round and improves the models' performance by either correcting or mitigating the effect of noisy samples. Our evaluation on various publicly available vision and audio datasets demonstrates a 22% improvement on average compared to other existing methods for a label noise level of 60%. We further validate the efficiency of FedLN in human-annotated real-world noisy datasets and report a 4.8% increase on average in models' recognition performance, highlighting that FedLN can be useful for improving FL services provided to everyday users. [ABSTRACT FROM AUTHOR]

Sleep stage classification is crucial for sleep state monitoring and health interventions. In accordance with the standards prescribed by the American Academy of Sleep Medicine, a sleep episode follows a specific structure comprising five distinctive sleep stages that collectively form a sleep cycle. Typically, this cycle repeats about five times, providing an insightful portrayal of the subject's physiological attributes. The progress of deep learning and advanced domain generalization methods allows automatic and even adaptive sleep stage classification. However, applying models trained with visible subject data to invisible subject data remains challenging due to significant individual differences among subjects. Motivated by the periodic category-complete structure of sleep stage classification, we propose a Structure Incentive Domain Adversarial learning (SIDA) method that combines the sleep stage classification method with domain generalization to enable cross-subject sleep stage classification. SIDA includes individual domain discriminators for each sleep stage category to decouple subject dependence differences among different categories and fine-grained learning of domain-invariant features. Furthermore, SIDA directly connects the label classifier and domain discriminators to promote the training process. Experiments on three benchmark sleep stage classification datasets demonstrate that the proposed SIDA method outperforms other state-of-the-art sleep stage classification and domain generalization methods and achieves the best cross-subject sleep stage classification results. [ABSTRACT FROM AUTHOR]

An Industrial Cyber-physical System (ICPS) provides a digital foundation for data-driven decision-making by artificial intelligence (AI) models. However, the poor data quality (e.g., inconsistent distribution, imbalanced classes) of high-speed, large-volume data streams poses significant challenges to the online deployment of offline-trained AI models. As an alternative, updating AI models online based on streaming data enables continuous improvement and resilient modeling performance. However, for a supervised learning model (i.e., a base learner), it is labor-intensive to annotate all streaming samples to update the model. Hence, a data acquisition method is needed to select the data for annotation to ensure data quality while saving annotation efforts. In the literature, active learning methods have been proposed to acquire informative samples. Different acquisition criteria were developed for exploration of under-represented regions in the input variable space or exploitation of the well-represented regions for optimal estimation of base learners. However, it remains a challenge to balance the exploration-exploitation trade-off under different online annotation scenarios. On the other hand, an acquisition criterion learned by AI adapts itself to a scenario dynamically, but the ambiguous consideration of the trade-off limits its performance in frequently changing manufacturing contexts. To overcome these limitations, we propose an ensemble active learning method by contextual bandits (CbeAL). CbeAL incorporates a set of active learning agents (i.e., acquisition criteria) explicitly designed for exploration or exploitation by a weighted combination of their acquisition decisions. The weight of each agent will be dynamically adjusted based on the usefulness of its decisions to improve the performance of the base learner. With adaptive and explicit consideration of both objectives, CbeAL efficiently guides the data acquisition process by selecting informative samples to reduce the human annotation efforts. Furthermore, we characterize the exploration and exploitation capability of the proposed agents theoretically. The evaluation results in a numerical simulation study and a real case study demonstrates the effectiveness and efficiency of CbeAL in manufacturing process modeling of the ICPS. [ABSTRACT FROM AUTHOR]

Back in 1988, the partial game trees explored by computer chess programs were among the largest search structures in real-world computing. Because the game tree is too large to be fully evaluated, chess programs must make heuristic strategic decisions based on partial information, making it an illustrative subject for teaching AI search. In one of his lectures that year on AI search for games and puzzles, Professor Hans Berliner—a pioneer of computer chess programs1—stated: "Intelligent heuristics are the future of computing." As a student in the field of the theory of computation, I was naturally perplexed but fascinated by this perspective. I had been trained to believe that "Algorithms and computational complexity theory are the foundation of computer science." However, as it happens, my attempts to understand heuristics in computing have subsequently played a significant role in my career as a theoretical computer scientist. I have come to realize that Berliner's postulation is a far-reaching worldview, particularly in the age of big, rich, complex, and multifaceted data and models, when computing has ubiquitous interactions with science, engineering, humanity, and society. In this article,2I will share some of my experiences on the subject of heuristics in computing, presenting examples of theoretical attempts to understand the behavior of heuristics on real data, as well as efforts to design practical heuristics with desirable theoretical characterizations. My hope is that these theoretical insights from past heuristics—such as spectral partitioning, multilevel methods, evolutionary algorithms, and simplex methods—can shed light on and further inspire a deeper understanding of the current and future techniques in AI and data mining. [ABSTRACT FROM AUTHOR]

Deep learning shows superiority in learning feature representations that offer promising performance in various application domains. Recent advances have shown that privacy attributes of users and patients (e.g., identity, gender, and race) can be accurately inferred from image data. To avoid the risk of privacy leaking, data owners can resort to releasing the embeddings rather than the original images. In this article, we aim at learning to generate privacy-preserving embeddings from image data. The obtained embeddings are required to maintain the data utility (e.g., keeping the performance of the main task, such as disease prediction) and to simultaneously prevent the private attributes of data instances from being accurately inferred. We also want the hard embeddings to be successfully used to reconstruct the original images. We propose a hybrid method based on multi-task learning to reach the goal. The key idea is twofold. One is to learn the feature encoder that can benefit the main task and fool the sensitive task at the same time via iterative training and feature disentanglement. The other is to incorporate the learning of adversarial examples to mislead the sensitive attribute classification's performance. Experiments conducted on Multi-Attribute Facial Landmark (MAFL) and NIH Chest X-ray datasets exhibit the effectiveness of our hybrid method. A set of advanced studies also shows the usefulness of each model component, the difficulty in data reconstruction, and the performance impact of task correlation. [ABSTRACT FROM AUTHOR]

Static scheduling of computational workflow represented by a directed acyclic graph (DAG) is an important problem in many areas of computer science. The main idea and novelty of the proposed algorithm is an adaptive heuristic or graph metric that uses a different heuristic rule at each scheduling step depending on local workflow. It is also important to note that multi-agent reinforcement learning is used to determine scheduling policy based on adaptive metrics. To prove the efficiency of the approach, a comparison with the state-of-the-art DAG scheduling algorithms is provided: DONF, CPOP, HCPT, HPS, and PETS. Based on the simulation results, the proposed algorithm shows an improvement of up to 30% on specific graph topologies and an average performance gain of 5.32%, compared to the best scheduling algorithm, DONF (suitable for large-scale scheduling), on a large number of random DAGs. Another important result is that using the proposed algorithm it was possible to cover 30.01% of the proximity interval from the best scheduling algorithm to the global optimal solution. This indicates that the idea of an adaptive metric for DAG scheduling is important and requires further research and development. [ABSTRACT FROM AUTHOR]

As computer architectures continue to integrate application-specific hardware, it is critical to understand the relative performance of devices for maximum app acceleration. The goal of benchmarking suites, such as MLPerf for analyzing machine learning (ML) hardware performance, is to standardize a fair comparison of different hardware architectures. However, there are many apps that are not well represented by these standards that require different workloads, such as ML models and datasets, to achieve similar goals. Additionally, many apps, like real-time video processing, are focused on latency of computations rather than strictly on throughput. This research analyzes multiple compute architectures that feature ML-specific hardware on a case study of handwritten Chinese character recognition. Specifically, AlexNet and a custom version of GoogLeNet are benchmarked in terms of their streaming latency and maximum throughput for optical character recognition. Considering that these models are composed of fundamental neural network operations yet architecturally different from each other, these models can stress devices in different yet insightful ways that generalizations of the performance of other models can be drawn from. Many devices featuring ML-specific hardware and optimizations are analyzed including Intel and AMD CPUs, Xilinx and Intel FPGAs, NVIDIA GPUs, and Google TPUs. Overall, ML-oriented hardware added to the Intel Xeon CPUs helps to boost throughput by 3.7× and to reduce latency by up to 34.7×, which makes the latency of Intel Xeon CPUs competitive on more parallel models. The TPU devices were limited in terms of throughput due to large data transfer times and not competitive in terms of latency. The FPGA frameworks showcase the lowest latency on the Xilinx Alveo U200 FPGA achieving 0.48 ms on AlexNet using Mipsology Zebra and 0.39 ms on GoogLeNet using Vitis-AI. Through their custom acceleration datapaths coupled with high-performance SRAM, the FPGAs are able to keep critical model data closer to processing elements for lower latency. The massively parallel and high-memory GPU devices with Tensor Core accelerators achieve the best throughput. The NVIDIA Tesla A100 GPU showcases the highest throughput at 42,513 and 52,484 images/second for AlexNet and GoogLeNet, respectively.1 [ABSTRACT FROM AUTHOR]

Anomaly analytics is a popular and vital task in various research contexts that has been studied for several decades. At the same time, deep learning has shown its capacity in solving many graph-based tasks, like node classification, link prediction, and graph classification. Recently, many studies are extending graph learning models for solving anomaly analytics problems, resulting in beneficial advances in graph-based anomaly analytics techniques. In this survey, we provide a comprehensive overview of graph learning methods for anomaly analytics tasks. We classify them into four categories based on their model architectures, namely graph convolutional network, graph attention network, graph autoencoder, and other graph learning models. The differences between these methods are also compared in a systematic manner. Furthermore, we outline several graph-based anomaly analytics applications across various domains in the real world. Finally, we discuss five potential future research directions in this rapidly growing field. [ABSTRACT FROM AUTHOR]

Being able to describe any user interface (UI) screenshot in natural language can promote understanding of the main purpose of the UI, yet currently it cannot be accomplished with state-of-the-art captioning systems. We introduce XUI, a novel method inspired by the global precedence effect to create informative descriptions of UIs, starting with an overview and then providing fine-grained descriptions about the most salient elements. XUI builds upon computational models for topic classification, visual saliency prediction, and natural language generation (NLG). XUI provides descriptions with up to three different granularity levels that, together, describe what is in the interface and what the user can do with it. We found that XUI descriptions are highly readable, are perceived to accurately describe the UI, and score similarly to human-generated UI descriptions. XUI is available as open-source software. [ABSTRACT FROM AUTHOR]

Human coders assign standardized medical codes to clinical documents generated during patients' hospitalization, which is error prone and labor intensive. Automated medical coding approaches have been developed using machine learning methods, such as deep neural networks. Nevertheless, automated medical coding is still challenging because of complex code association, noise in lengthy documents, and the imbalanced class problem. We propose a novel neural network, called the Multitask Balanced and Recalibrated Neural Network, to solve these issues. Significantly, the multitask learning scheme shares the relationship knowledge between different coding branches to capture code association. A recalibrated aggregation module is developed by cascading convolutional blocks to extract high-level semantic features that mitigate the impact of noise in documents. Also, the cascaded structure of the recalibrated module can benefit learning from lengthy notes. To solve the imbalanced class problem, we deploy focal loss to redistribute the attention on low- and high-frequency medical codes. Experimental results show that our proposed model outperforms competitive baselines on a real-world clinical dataset called the Medical Information Mart for Intensive Care (MIMIC-III). [ABSTRACT FROM AUTHOR]

Context: Coding is an incremental activity where a developer may need to understand a code before making suitable changes in the code. Code documentation is considered one of the best practices in software development but requires significant efforts from developers. Recent advances in natural language processing and machine learning have provided enough motivation to devise automated approaches for source code documentation at multiple levels. Objective: The review aims to study current code documentation practices and analyze the existing literature to provide a perspective on their preparedness to address the stated problem and the challenges that lie ahead. Methodology: We provide a detailed account of the literature in the area of automated source code documentation at different levels and critically analyze the effectiveness of the proposed approaches. This also allows us to infer gaps and challenges to address the problem at different levels. Findings: (1) The research community focused on method-level summarization. (2) Deep learning has dominated the past five years of this research field. (3) Researchers are regularly proposing bigger corpora for source code documentation. (4) Java and Python are the widely used programming languages as corpus. (5) Bilingual Evaluation Understudy is the most favored evaluation metric for the research persons. [ABSTRACT FROM AUTHOR]

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g., cryptography (Homomorphic Encryption (HE), Differential Privacy (DP)) and collaborative training (Secure Multi-Party Computation (MPC), Distributed Learning, and Federated Learning (FL)). These techniques have a particular focus on data encryption or secure local computation. They transfer the intermediate information to the third party to compute the final result. Gradient exchanging is commonly considered to be a secure way of training a robust model collaboratively in Deep Learning (DL). However, recent researches have demonstrated that sensitive information can be recovered from the shared gradient. Generative Adversarial Network (GAN), in particular, has shown to be effective in recovering such information. However, GAN based techniques require additional information, such as class labels that are generally unavailable for privacy-preserved learning. In this article, we show that, in the FL system, image-based privacy data can be easily recovered in full from the shared gradient only via our proposed Generative Regression Neural Network (GRNN). We formulate the attack to be a regression problem and optimize two branches of the generative model by minimizing the distance between gradients. We evaluate our method on several image classification tasks. The results illustrate that our proposed GRNN outperforms state-of-the-art methods with better stability, stronger robustness, and higher accuracy. It also has no convergence requirement to the global FL model. Moreover, we demonstrate information leakage using face re-identification. Some defense strategies are also discussed in this work. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy. [ABSTRACT FROM AUTHOR]

Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR). However, the generated image still suffers from undesirable artifacts such as the absence of texture-feature representation and high-frequency information. We propose a frequency domain-based spatio-temporal remote sensing single image super-resolution technique to reconstruct the HR image combined with generative adversarial networks (GANs) on various frequency bands (TWIST-GAN). We have introduced a new method incorporating Wavelet Transform (WT) characteristics and transferred generative adversarial network. The LR image has been split into various frequency bands by using the WT, whereas the transfer generative adversarial network predicts high-frequency components via a proposed architecture. Finally, the inverse transfer of wavelets produces a reconstructed image with super-resolution. The model is first trained on an external DIV2 K dataset and validated with the UC Merced Landsat remote sensing dataset and Set14 with each image size of 256 × 256. Following that, transferred GANs are used to process spatio-temporal remote sensing images in order to minimize computation cost differences and improve texture information. The findings are compared qualitatively and qualitatively with the current state-of-art approaches. In addition, we saved about 43% of the GPU memory during training and accelerated the execution of our simplified version by eliminating batch normalization layers. [ABSTRACT FROM AUTHOR]

In the emerging business of food delivery, rider traffic accidents raise financial cost and social traffic burden. Although there has been much effort on traffic accident forecasting using temporal-spatial prediction models, none of the existing work studies the problem of detecting the takeaway rider accidents based on food delivery trajectory data. In this article, we aim to detect whether a takeaway rider meets an accident on a certain time period based on trajectories of food delivery and riders' contextual information. The food delivery data has a heterogeneous information structure and carries contextual information such as weather and delivery history, and trajectory data are collected as a spatial-temporal sequence. In this article, we propose a TakeAwayRiderAccident detection fusion network TARA-Net to jointly model these heterogeneous and spatial-temporal sequence data. We utilize the residual network to extract basic contextual information features and take advantage of a transformer encoder to capture trajectory features. These embedding features are concatenated into a pyramidal feed-forward neural network. We jointly train the above three components to combine the benefits of spatial-temporal trajectory data and sparse basic contextual data for early detecting traffic accidents. Furthermore, although traffic accidents rarely happen in food delivery, we propose a sampling mechanism to alleviate the imbalance of samples when training the model. We evaluate the model on a transportation mode classification dataset Geolife and a real-world Ele.me dataset with over 3 million riders. The experimental results show that the proposed model is superior to the state-of-the-art. [ABSTRACT FROM AUTHOR]

As a critical task in intelligent traffic systems, traffic prediction has received a large amount of attention in the past few decades. The early efforts mainly model traffic prediction as the time-series mining problem, in which the spatial dependence has been largely ignored. As the rapid development of deep learning, some attempts have been made in modeling traffic prediction as the spatio-temporal data mining problem in a road network, in which deep learning techniques can be adopted for modeling the spatial and temporal dependencies simultaneously. Despite the success, the spatial and temporal dependencies are only modeled in a regionless network without considering the underlying hierarchical regional structure of the spatial nodes, which is an important structure naturally existing in the real-world road network. Apart from the challenge of modeling the spatial and temporal dependencies like the existing studies, the extra challenge caused by considering the hierarchical regional structure of the road network lies in simultaneously modeling the spatial and temporal dependencies between nodes and regions and the spatial and temporal dependencies between regions. To this end, this article proposes a new Temporal Hierarchical Graph Attention Network (TH-GAT). The main idea lies in augmenting the original road network into a region-augmented network, in which the hierarchical regional structure can be modeled. Based on the region-augmented network, the region-aware spatial dependence model and the region-aware temporal dependence model can be constructed, which are two main components of the proposed TH-GAT model. In addition, in the region-aware spatial dependence model, the graph attention network is adopted, in which the importance of a node to another node, of a node to a region, of a region to a node, and of a region to another region, can be captured automatically by means of the attention coefficients. Extensive experiments are conducted on two real-world traffic datasets, and the results have confirmed the superiority of the proposed TH-GAT model. [ABSTRACT FROM AUTHOR]

Grammatical error correction (GEC) is an important application aspect of natural language processing techniques, and GEC system is a kind of very important intelligent system that has long been explored both in academic and industrial communities. The past decade has witnessed significant progress achieved in GEC for the sake of increasing popularity of machine learning and deep learning. However, there is not a survey that untangles the large amount of research works and progress in this field. We present the first survey in GEC for a comprehensive retrospective of the literature in this area. We first give the definition of GEC task and introduce the public datasets and data annotation schema. After that, we discuss six kinds of basic approaches, six commonly applied performance boosting techniques for GEC systems, and three data augmentation methods. Since GEC is typically viewed as a sister task of Machine Translation (MT), we put more emphasis on the statistical machine translation (SMT)-based approaches and neural machine translation (NMT)-based approaches for the sake of their importance. Similarly, some performance-boosting techniques are adapted from MT and are successfully combined with GEC systems for enhancement on the final performance. More importantly, after the introduction of the evaluation in GEC, we make an in-depth analysis based on empirical results in aspects of GEC approaches and GEC systems for a clearer pattern of progress in GEC, where error type analysis and system recapitulation are clearly presented. Finally, we discuss five prospective directions for future GEC researches. [ABSTRACT FROM AUTHOR]

Ensemble learning is a widely used technique to train deep convolutional neural networks (CNNs) for improved robustness and accuracy. While existing algorithms usually first train multiple diversified networks and then assemble these networks as an aggregated classifier, we propose a novel learning paradigm, namely, "In-Network Ensemble" (INE) that incorporates the diversity of multiple models through training a SINGLE deep neural network. Specifically, INE segments the outputs of the CNN into multiple independent classifiers, where each classifier is further fine-tuned with better accuracy through a so-called diversified knowledge distillation process. We then aggregate the fine-tuned independent classifiers using an Averaging-and-Softmax operator to obtain the final ensemble classifier. Note that, in the supervised learning settings, INE starts the CNN training from random, while, under the transfer learning settings, it also could start with a pre-trained model to incorporate the knowledge learned from additional datasets. Extensive experiments have been done using eight large-scale real-world datasets, including CIFAR, ImageNet, and Stanford Cars, among others, as well as common deep network architectures such as VGG, ResNet, and Wide ResNet. We have evaluated the method under two tasks: supervised learning and transfer learning. The results show that INE outperforms the state-of-the-art algorithms for deep ensemble learning with improved accuracy. [ABSTRACT FROM AUTHOR]

Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems of "topic identification" and "text segmentation" for sparse document learning, when there is a single new text of interest. In developing a methodology to handle single documents, we face two major challenges. First is sparse information: with access to only one document, we cannot train traditional topic models or deep learning algorithms. Second is significant noise: a considerable portion of words in any single document will produce only noise and not help discern topics or segments. To tackle these issues, we design an unsupervised, computationally efficient methodology called Biclustering Approach to Topic modeling and Segmentation (BATS). BATS leverages three key ideas to simultaneously identify topics and segment text: (i) a new mechanism that uses word order information to reduce sample complexity, (ii) a statistically sound graph-based biclustering technique that identifies latent structures of words and sentences, and (iii) a collection of effective heuristics that remove noise words and award important words to further improve performance. Experiments on six datasets show that our approach outperforms several state-of-the-art baselines when considering topic coherence, topic diversity, segmentation, and runtime comparison metrics. [ABSTRACT FROM AUTHOR]

Delivery stations play important roles in logistics systems. Well-designed delivery station planning can improve delivery efficiency significantly. However, existing delivery station locations are decided by experts, which requires much preliminary research and data collection work. It is not only time consuming but also expensive for logistics companies. Therefore, in this article, we propose a data-driven pipeline that can transfer expert knowledge among cities and automatically allocate delivery stations. Based on existing well-designed station location planning in the source city, we first train a model to learn the expert knowledge about delivery range selection for each station. Then we transfer the learned knowledge to a new city and design three strategies to select delivery stations for the new city. Due to the differences in characteristics among different cities, we adopt a transfer learning method to eliminate the domain difference so that the model can be adapted to a new city well. Finally, we conduct extensive experiments based on real-world datasets and find the proposed method can solve the problem well. [ABSTRACT FROM AUTHOR]

Using unreliable information sources generating conflicting evidence may lead to a large uncertainty, which significantly hurts the decision making process. Recently, many approaches have been taken to integrate conflicting data from multiple sources and/or fusing conflicting opinions from different entities. To explicitly deal with uncertainty, a belief model called Subjective Logic (SL), as a variant of Dumpster-Shafer Theory, has been proposed to represent subjective opinions and to merge multiple opinions by offering a rich volume of fusing operators, which have been used to solve many opinion inference problems in trust networks. However, the operators of SL are known to be lack of scalability in inferring unknown opinions from large network data as a result of the sequential procedures of merging multiple opinions. In addition, SL does not consider deriving opinions in the presence of conflicting evidence. In this work, we propose a hybrid inference method that combines SL and Probabilistic Soft Logic (PSL), namely, Collective Subjective Plus, CSL+, which is resistible to highly conflicting evidence or a lack of evidence. PSL can reason a belief in a collective manner to deal with large-scale network data, allowing high scalability based on relationships between opinions. However, PSL does not consider an uncertainty dimension in a subjective opinion. To take benefits from both SL and PSL, we proposed a hybrid approach called CSL+ for achieving high scalability and high prediction accuracy for unknown opinions with uncertainty derived from a lack of evidence and/or conflicting evidence. Through the extensive experiments on four semi-synthetic and two real-world datasets, we showed that the CSL+ outperforms the state-of-the-art belief model (i.e., SL), probabilistic inference models (i.e., PSL, CSL), and deep learning model (i.e., GCN-VAE-opinion) in terms of prediction accuracy, computational complexity, and real running time. [ABSTRACT FROM AUTHOR]

Face anti-spoofing aims to detect presentation attack to face recognition--based authentication systems. It has drawn growing attention due to the high security demand. The widely adopted CNN-based methods usually well recognize the spoofing faces when training and testing spoofing samples display similar patterns, but their performance would drop drastically on testing spoofing faces of novel patterns or unseen scenes, leading to poor generalization performance. Furthermore, almost all current methods treat face anti-spoofing as a prior step to face recognition, which prolongs the response time and makes face authentication inefficient. In this article, we try to boost the generalizability and applicability of face anti-spoofing methods by designing a new generalizable face authentication CNN (GFA-CNN) model with three novelties. First, GFA-CNN introduces a simple yet effective total pairwise confusion loss for CNN training that properly balances contributions of all spoofing patterns for recognizing the spoofing faces. Second, it incorporate a fast domain adaptation component to alleviate negative effects brought by domain variation. Third, it deploys filter diversification learning to make the learned representations more adaptable to new scenes. In addition, the proposed GFA-CNN works in a multi-task manner—it performs face anti-spoofing and face recognition simultaneously. Experimental results on five popular face anti-spoofing and face recognition benchmarks show that GFA-CNN outperforms previous face anti-spoofing methods on cross-test protocols significantly and also well preserves the identity information of input face images. [ABSTRACT FROM AUTHOR]

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but different target domain with the goal of performing well at test-time on the target domain. Many single-source and typically homogeneous unsupervised deep domain adaptation approaches have thus been developed, combining the powerful, hierarchical representations from deep learning with domain adaptation to reduce reliance on potentially costly target data labels. This survey will compare these approaches by examining alternative methods, the unique and common elements, results, and theoretical insights. We follow this with a look at application areas and open research directions. [ABSTRACT FROM AUTHOR]

The development of smart vehicles brings drivers and passengers a comfortable and safe environment. Various emerging applications are promising to enrich users' traveling experiences and daily life. However, how to execute computing-intensive applications on resource-constrained vehicles still faces huge challenges. In this article, we construct an intelligent offloading system for vehicular edge computing by leveraging deep reinforcement learning. First, both the communication and computation states are modelled by finite Markov chains. Moreover, the task scheduling and resource allocation strategy is formulated as a joint optimization problem to maximize users' Quality of Experience (QoE). Due to its complexity, the original problem is further divided into two sub-optimization problems. A two-sided matching scheme and a deep reinforcement learning approach are developed to schedule offloading requests and allocate network resources, respectively. Performance evaluations illustrate the effectiveness and superiority of our constructed system. [ABSTRACT FROM AUTHOR]

Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which can handle extra-large-scale tasks with great performance is widely needed. Deep forest is a recently proposed deep learning framework which uses tree ensembles as its building blocks and it has achieved highly competitive results on various domains of tasks. However, it has not been tested on extremely large-scale tasks. In this work, based on our parameter server system, we developed the distributed version of deep forest. To meet the need for real-world tasks, many improvements are introduced to the original deep forest model, including MART (Multiple Additive Regression Tree) as base learners for efficiency and effectiveness consideration, the cost-based method for handling prevalent class-imbalanced data, MART based feature selection for high dimension data, and different evaluation metrics for automatically determining the cascade level. We tested the deep forest model on an extra-large-scale task, i.e., automatic detection of cash-out fraud, with more than 100 million training samples. Experimental results showed that the deep forest model has the best performance according to the evaluation metrics from different perspectives even with very little effort for parameter tuning. This model can block fraud transactions in a large amount of money each day. Even compared with the best-deployed model, the deep forest model can additionally bring a significant decrease in economic loss each day. [ABSTRACT FROM AUTHOR]