Search

Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains. In this article, we study the multisource HDA problem and propose a conditional weighting adversarial network (CWAN) to address it. The proposed CWAN adversarially learns a feature transformer, a label classifier, and a domain discriminator. To quantify the importance of different source domains, CWAN introduces a sophisticated conditional weighting scheme to calculate the weights of the source domains according to the conditional distribution divergence between the source and target domains. Different from existing weighting schemes, the proposed conditional weighting scheme not only weights the source domains but also implicitly aligns the conditional distributions during the optimization process. Experimental results clearly demonstrate that the proposed CWAN performs much better than several state-of-the-art methods on four real-world datasets.

The near-surface temperature prediction (NTP) is an important spatial-temporal forecast problem, which can be used to prevent temperature crises. Most of the previous approaches fail to explicitly model the long- and short-range spatial correlations simultaneously, which is critical to making an accurate temperature prediction. In this study, both long- and short-range spatial correlations are captured to fill this gap by a novel convolution operator named Long- and Short-range Convolution (LS-Conv). The proposed LS-Conv operator includes three key components, namely, Node-based Spatial Attention (NSA), Long-range Adaptive Graph Constructor (LAGC), and Long- and Short-range Integrator (LSI). To capture long-range spatial correlations, NSA and LAGC are proposed to evaluate node importance aiming at auto-constructing long-range spatial correlations, which is named as Long-range aware Graph Convolution Network (LR-GCN). After that, the Short-range aware Convolution Neural Network (SR-CNN) accounts for the short-range spatial correlations. Finally, LSI is proposed to capture both long- and short-range spatial correlations by intra-unifying LR-GCN and SR-CNN. Upon the proposed LS-Conv operator, a new model called Long- and Short-range for NPT (LS-NTP) is developed. Extensive experiments are conducted on two real-world datasets and the results demonstrate that the proposed method outperforms state-of-the-art techniques. The source code is available on GitHub:https://github.com/xuguangning1218/LS_NTP.

A typhoon is a destructive weather system that can cause severe casualties and economic losses. Typhoon intensity (TI) is a measurement to evaluate its ruinous degree. Hence, typhoon intensity prediction is an important research problem and many methods have been proposed. However, most of the existing approaches have very limited capability to combine the 2D Typhoon Structure Domain-expert Knowledge (2D-TSDK) and the 3D Typhoon Structure Data-driven Knowledge (3D-TSDK) for the TI prediction. To address this issue, this paper proposes a spatio-temporal deep learning method named Spatial Attention Fusing Network (SAF-Net). The designed model aims to fuse the 2D-TSDK and the 3D-TSDK by developing a specific Wide & Deep framework. In the data-driven component, a special Spatial Attention (SA) module is designed to automatically select high-response wind speed areas and embedded into a three-branch CNN to exploit the 3D-TSDK. Then, the Wide & Deep framework integrates the 2D-TSDK and the 3D-TSDK for the TI prediction. Comprehensive experiments have been conducted on a real-world dataset, and the result shows that the proposed method outperforms state-of-the-art typhoon intensity prediction methods. The code is available in GitHub: https://github.com/xuguangning1218/TI_Prediction

Due to the degeneration problem of sensors, calibration becomes a prerequisite step to retrieve consistent satellite images, especially for the ones from long-term time series. Relative calibration is an economic manner to address the problem. Previous studies leverage the identified no-change pixels (NCPs) between two images for relative calibration. However, the identification of NCPs itself is a very hard task and the inferior detection quality affects the performances significantly. Inspired by the great success of deep learning techniques, in this article, we first develop a convolutional neural network (CNN)-based relative calibration method, which bypasses the NCP detection. In particular, the ratio of sensor sensitivity coefficients at two time points is directly estimated by feeding the corresponding image pair into our developed CNN regressor. A polynomial function is fitted upon the estimated ratios in time series. We train the CNN regressor based on the multisite calibration results and then conduct experiments on FengYun-3A (FY-3A), FengYun-3B (FY-3B), and FengYun-3C (FY-3C). The results validate the effectiveness of the proposed method, and it outperforms state-of-the-art NCP-based methods.

Poverty prediction is an important task for developing countries that lack the key measures of economic development. The prediction can help governments to allocate scarce resources for sustainable development. Nighttime satellite imagery offers an opportunity to address the task. However, as the nighttime satellite data contain a large amount of noise, directly leveraging it is not very effective. Previous studies have shown that relying on deep learning techniques nighttime satellite data can be a good proxy between daytime satellite imagery and the poverty index. In this letter, based on the proxy, we leverage four deep learning approaches, namely, VGG-Net, Inception-Net, ResNet, and DenseNet, to extract deep features from daytime satellite imagery and then apply least absolute shrinkage and selection operator (LASSO) regression for poverty prediction. To further enhance the performance, we also integrate the squeeze and excitation (SE) module and focal loss into ResNet and DenseNet. Experimental results demonstrate the effectiveness of the investigated approaches, and the DenseNet with SE module and focal loss performs the best.

Precipitation nowcasting is an important task, which can serve numerous applications such as urban alert and transportation. Previous studies leverage convolutional recurrent neural networks (RNNs) to address the problem. However, they all suffer from two inherent drawbacks of the convolutional RNN, namely, the lack of a memory cell to preserve the fine-grained spatial appearances and the position misalignment issue when combining current observations with previous hidden states. In this article, we aim to overcome the defects. Specifically, we propose a novel pseudo flow spatiotemporal LSTM unit (PFST-LSTM), where a spatial memory cell and a position alignment module are developed and embedded in the structure of LSTM. Upon the PFST-LSTM units, we develop a new sequence-to-sequence architecture for precipitation nowcasting, which can effectively combine the spatial appearances and motion information. Extensive empirical evaluations are conducted on synthetic MovingMNIST++ and CIKM AnalytiCup 2017 datasets. Our experimental results demonstrate the superiority of the proposed PFST-LSTM over the state-of-the-art competitors. To reproduce the results, we release the source code at: https://github.com/luochuyao/PFST-LSTM .

Reinforcement learning (RL) techniques have recently been introduced to recommender systems. Most existing research works focus on designing policy and learning algorithms of the recommender agent but seldom care about the top-aware issue, i.e., the performance on the top positions is not satisfying, which is crucial for real applications. To address the drawback, we propose a Supervised deep Reinforcement learning Recommendation framework named as SRR. Within this framework, we utilize a supervised learning (SL) model to partially guide the learning of recommendation policy, where the supervision signal and RL signal are jointly employed and updated in a complementary fashion. We empirically find that suitable weak supervision helps to balance the immediate reward and the long-term reward, which nicely addresses the top-aware issue in RL based recommendation. Moreover, we perform a further investigation on how different supervision signals impact on recommendation policy. Extensive experiments are carried out on two real-world datasets under both the offline and simulated online evaluation settings, and the results demonstrate that the proposed methods indeed resolve the top-aware issue without much performance sacrifice in the long-run, compared with the state-of-the-art methods.

Precipitation nowcasting is an important task in operational weather forecasts. The key challenge of the task is the radar echo map extrapolation. The problem is mainly solved by an optical-flow method in existing systems. However, the method cannot model rapid and nonlinear movements. Recently, a convolutional gated recurrent unit (ConvGRU) method is developed, which aims to model such movements based on deep learning techniques. Despite the promising performance, ConvGRU tends to yield blurring extrapolation images and fails to multi-modal and skewed intensity distribution. To overcome the limitations, we propose in this letter a generative adversarial ConvGRU (GA-ConvGRU) model. The model is composed of two adversarial learning systems, which are a ConvGRU-based generator and a convolution neural network-based discriminator. The two systems are trained by playing a minimax game. With the adversarial learning scheme, GA-ConvGRU can yield more realistic and more accurate extrapolation. Experiments on real data sets have been conducted and the results demonstrate that the proposed GA-ConvGRU significantly outperforms state-of-the-art extrapolation methods ConvGRU and optical flow.

Aspect-based (aspect-level) sentiment analysis is an important task in fine-grained sentiment analysis, which aims to automatically infer the sentiment towards an aspect in its context. Previous studies have shown that utilizing the attention-based method can effectively improve the accuracy of the aspect-based sentiment analysis. Despite the outstanding progress, aspect-based sentiment analysis in the real-world remains several challenges. (1) The current attention-based method may cause a given aspect to incorrectly focus on syntactically unrelated words. (2) Conventional methods fail to identify the sentiment with the special sentence structure, such as double negatives. (3) Most of the studies leverage only one vector to represent context and target. However, utilizing one vector to represent the sentence is limited, as the natural languages are delicate and complex. In this paper, we propose a knowledge guided capsule network (KGCapsAN), which can address the above deficiencies. Our method is composed of two parts, a Bi-LSTM network and a capsule attention network. The capsule attention network implements the routing method by attention mechanism. Moreover, we utilize two prior knowledge to guide the capsule attention process, which are syntactical and n-gram structures. Extensive experiments are conducted on six datasets, and the results show that the proposed method yields the state-of-the-art.

Cross-modal hashing is an important technology for large-scale very high resolution (VHR) and synthetic-aperture radar (SAR) image retrieval. Current cross-modal hashing methods fail to effectively preserve the intra-class similarities and the inter-class discriminations between VHR and SAR images when learning common semantic representation of these cross-modal images. This is because these methods use derived signals to implicitly guide hashing learning, which leads to low discrimination of generated hash codes. To address the drawback, this paper proposes an explicit semantic preserving-based deep hashing method, which can fully learn the intra-class and inter-class semantic structure. Specifically, we design a novel objective function to explicitly preserve the intra-class and inter-class semantic structure directly with class labels. Extensive experiments on a VHR-SAR dataset demonstrate that our method outperforms various state-of-the-art cross-modal hashing methods.

Wind power is a new type of green energy. Though it is economical to access and gather such energy, effectively matching the energy with consumers' demand is difficult, because of the fluctuate, intermittent and chaotic nature of wind speed. Hence, multi-step wind speed prediction becomes an important research topic. In this paper, we propose a novel deep learning method, DyanmicNet, for the problem. DynamicNet follows an encoder-decoder framework. To capture the fluctuate, intermittent and chaotic nature of wind speed, it leverages a time-variant structure to build the decoder, which is different from conventional encoder-decoder methods. In addition, a new neural block (ST-GRU-ODE) is developed, which can model the wind speed in a continuous manner by using the neural ordinary differential equation (ODE). To enhance the prediction performance, a multi-step training procedure is also put forward. Comprehensive experiments have been conducted on two real-world datasets, where wind speed is recorded in the form of two orthogonal components namely U-Wind and V-Wind. Each component can be illustrated as wind speed images. Experimental results demonstrate the effectiveness and superiority of the proposed method over state-of-the-art techniques.

Road information extraction based on aerial images is a critical task for many applications, and it has attracted considerable attention from researchers in the field of remote sensing. The problem is mainly composed of two subtasks, namely, road detection and centerline extraction. Most of the previous studies rely on multistage-based learning methods to solve the problem. However, these approaches may suffer from the well-known problem of propagation errors. In this paper, we propose a novel deep learning model, recurrent convolution neural network U-Net (RCNN-UNet), to tackle the aforementioned problem. Our proposed RCNN-UNet has three distinct advantages. First, the end-to-end deep learning scheme eliminates the propagation errors. Second, a carefully designed RCNN unit is leveraged to build our deep learning architecture, which can better exploit the spatial context and the rich low-level visual features. Thereby, it alleviates the detection problems caused by noises, occlusions, and complex backgrounds of roads. Third, as the tasks of road detection and centerline extraction are strongly correlated, a multitask learning scheme is designed so that two predictors can be simultaneously trained to improve both effectiveness and efficiency. Extensive experiments were carried out based on two publicly available benchmark data sets, and nine state-of-the-art baselines were used in a comparative evaluation. Our experimental results demonstrate the superiority of the proposed RCNN-UNet model for both the road detection and the centerline extraction tasks.

Most of existing image categorizations assume that the given datasets have a good resolution and quality. However, the assumption is often violated in real applications. In this paper, we study the low-resolution (LR) image categorization. By utilizing labeled high-resolution (HR) images as auxiliary information, we formulate the problem as a heterogeneous domain adaptation problem and propose a Discriminative Joint Distribution Adaptation (DJDA) model to solve it. The DJDA model projects both LR and HR images into an intermediate subspace with a well-designed objective function, where the distance between classes is expected to be enlarged and the distribution divergence to be reduced. As a result, the discriminative knowledge for HR images can be transferred effectively to LR images. Experimental results demonstrate the proposed DJDA method produces significantly superior categorization accuracies against state-of-the-art competitors.

Wildfires are a serious disaster, which often cause severe damages to forests and plants. Without an early detection and suitable control action, a small wildfire could grow into a big and serious one. The problem is especially fatal at night, as firefighters in general miss the chance to detect the wildfires in the very first few hours. Low-light satellites, which take pictures at night, offer an opportunity to detect night fire timely. However, previous studies identify night fires based on threshold methods or conventional machine learning approaches, which are not robust and accurate enough. In this paper, we develop a new deep learning approach, which determines night fire locations by a pixel-level classification on low-light remote sensing image. Experimental results on VIIRS data demonstrate the superiority and effectiveness of the proposed method, which outperforms conventional threshold and machine learning approaches.

Few-shot learning aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. However, results show that the fine-tuning step makes marginal improvements. In this paper, 1) we figure out the reason, i.e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning feature extractor is less meaningful; 2) instead of fine-tuning feature extractor, we focus on estimating more representative prototypes. Consequently, we propose a novel prototype completion based meta-learning framework. This framework first introduces primitive knowledge (i.e., class-level part or attribute annotations) and extracts representative features for seen attributes as priors. Second, a part/attribute transfer network is designed to learn to infer the representative features for unseen attributes as supplementary priors. Finally, a prototype completion network is devised to learn to complete prototypes with these priors. Moreover, to avoid the prototype completion error, we further develop a Gaussian based prototype fusion strategy that fuses the mean-based and completed prototypes by exploiting the unlabeled samples. Extensive experiments show that our method: (i) obtains more accurate prototypes; (ii) achieves superior performance on both inductive and transductive FSL settings., Comment: Extended version of 'Prototype Completion with Primitive Knowledge for Few-Shot Learning' in CVPR2021. arXiv admin note: substantial text overlap with arXiv:2009.04960

Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hyperspectral images. On the other hand, few approaches make use of both spectral and spatial information simultaneously, which is critical to accurate hyperspectral image classification. This paper presents a novel Synergistic Convolutional Neural Network (SyCNN) for accurate hyperspectral image classification. The SyCNN consists of a hybrid module that combines 2D and 3D CNNs in feature learning and a data interaction module that fuses spectral and spatial hyperspectral information. Additionally, it introduces a 3D attention mechanism before the fully-connected layer which helps filter out interfering features and information effectively. Extensive experiments over three public benchmarking datasets show that our proposed SyCNNs clearly outperform state-of-the-art techniques that use 2D/3D CNNs. Published version

This paper proposes Dual-attentional Factorization-Machines (DFM), which incorporates global-wise attention and element-wise attention with FM for user response prediction. We further extend DFM with a deep neural network and name this new model Dual-attentional Factorization-machines based Network (DFNet). Comprehensive experiments are conducted on two real-world datasets to demonstrate the effectiveness of DFM and DFNet over the state-of-the-art models for user response prediction.

The research of reinforcement learning (RL) based recommendation method has become a hot topic in recommendation community, due to the recent advance in interactive recommender systems. The existing RL recommendation approaches can be summarized into a unified framework with three components, namely embedding component (EC), state representation component (SRC) and policy component (PC). We find that EC cannot be nicely trained with the other two components simultaneously. Previous studies bypass the obstacle through a pre-training and fixing strategy, which makes their approaches unlike a real end-to-end fashion. More importantly, such pre-trained and fixed EC suffers from two inherent drawbacks: (1) Pre-trained and fixed embeddings are unable to model evolving preference of users and item correlations in the dynamic environment; (2) Pre-training is inconvenient in the industrial applications. To address the problem, in this paper, we propose an End-to-end Deep Reinforcement learning based Recommendation framework (EDRR). In this framework, a supervised learning signal is carefully designed for smoothing the update gradients to EC, and three incorporating ways are introduced and compared. To the best of our knowledge, we are the first to address the training compatibility between the three components in RL based recommendations. Extensive experiments are conducted on three real-world datasets, and the results demonstrate the proposed EDRR effectively achieves the end-to-end training purpose for both policy-based and value-based RL models, and delivers better performance than state-of-the-art methods.

Stance detection is an important task, which aims to classify the attitude of an opinionated text towards a given target. Remarkable success has been achieved when sufficient labeled training data is available. However, annotating sufficient data is labor-intensive, which establishes significant barriers for generalizing the stance classifier to the data with new targets. In this paper, we proposed a Semantic-Emotion Knowledge Transferring (SEKT) model for cross-target stance detection, which uses the external knowledge (semantic and emotion lexicons) as a bridge to enable knowledge transfer across different targets. Specifically, a semantic-emotion heterogeneous graph is constructed from external semantic and emotion lexicons, which is then fed into a graph convolutional network to learn multi-hop semantic connections between words and emotion tags. Then, the learned semantic-emotion graph representation, which serves as prior knowledge bridging the gap between the source and target domains, is fully integrated into the bidirectional long short-term memory (BiLSTM) stance classifier by adding a novel knowledge-aware memory unit to the BiLSTM cell. Extensive experiments on a large real-world dataset demonstrate the superiority of SEKT against the state-of-the-art baseline methods.

Few-shot learning is a challenging task, which aims to learn a classifier for novel classes with few examples. Pre-training based meta-learning methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. However, results show that the fine-tuning step makes very marginal improvements. In this paper, 1) we figure out the key reason, i.e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning the feature extractor is less meaningful; 2) instead of fine-tuning the feature extractor, we focus on estimating more representative prototypes during meta-learning. Consequently, we propose a novel prototype completion based meta-learning framework. This framework first introduces primitive knowledge (i.e., class-level part or attribute annotations) and extracts representative attribute features as priors. Then, we design a prototype completion network to learn to complete prototypes with these priors. To avoid the prototype completion error caused by primitive knowledge noises or class differences, we further develop a Gaussian based prototype fusion strategy that combines the mean-based and completed prototypes by exploiting the unlabeled samples. Extensive experiments show that our method: (i) can obtain more accurate prototypes; (ii) outperforms state-of-the-art techniques by 2% - 9% in terms of classification accuracy. Our code is available online., Comment: Accepted by CVPR2021

Multivariate Time Series Classification (MTSC) is believed to be a crucial task towards dynamic process recognition and has been widely studied. Recent years, end-to-end MTSC with Convolutional Neural Network (CNN) has gained increasing attention thanks to its ability to integrates local features. However, it remains a significant challenge for CNN to handle global information and long-range dependencies of time series. In this paper, we present a simple and feasible architecture for MTSC to address these problems. Our model benefits from self-attention, which can help CNN directly capture the relationships of time series between two random time steps or variables. Experimental results of the proposed model work on thirty five complex MTSC tasks show its effectiveness and universality that has to outperform existing state-of-the-art (SOTA) model overall. Besides, our model is computationally efficient, and the parsing speed is six hours faster than the current model.

Relation extraction is an important task in natural language processing. To obtain a large amount of annotated data, distant supervision is introduced by using large-scale knowledge graphs as external resources. The disadvantage is that distant supervision brings a new issue: noise label, which means the labels obtained by distant supervision may be unreliable and the performance of the models decreases significantly on these datasets. To address the problem, we propose a new framework where noise labels are modeled directly by context-dependent rectification strategy. Intuitively, we adjust the labels that might otherwise be wrong in the right direction. In addition, considering the lack of effective guidance in training with noise, we propose a new curriculum learning-based adaptive mechanism. It learns simple relation extraction task first, then takes the reliability of labels into consideration, so that the model can learn more from the data. The experimental results on a widely used dataset show a significant improvement in our approach and outperform current state-of-the-art.

Sequence anomaly detection in time series is of critical importance to wide applications ranging from finance, healthcare to IT system monitoring. Most current researches use the reconstruction-based deep learning algorithms to solve the problem. In this article, we aim to use a prediction-based method to detect sequence anomalies in univariate time series, because the latter methods can detect anomalies using historical information revealing normal patterns in time series whereas the former methods simply consider current sequences. However, it is challenging because there exists both uncertainty in the future and performance deterioration under long detection horizon. To tackle the challenges, we propose an unsupervised algorithm called KfreqGAN, which is based on adversarially trained sequence predictor. The adversarial learning architecture helps the model make accurate predictions for future sequences. In addition, auxiliary information from frequency domain is used to help the model capture the characteristics of time series for achieving satisfactory predictions. We conduct extensive experiments on two public-available datasets, with results demonstrating the effectiveness of the proposed algorithm and its superiority to baseline algorithms.

Network embedding aims to learn low-dimensional representations for nodes in social networks, which can serve many applications, such as node classification, link prediction and visualization. Most of network embedding methods focus on learning the representations solely from the topological structure. Recently, attributed network embedding, which utilizes both the topological structure and node content to jointly learn latent representations, becomes a hot topic. However, previous studies obtain the joint representations by directly concatenating the one from each aspect, which may lose the correlations between the topological structure and node content. In this paper, we propose a new attributed network embedding method, TLVANE, which can address the drawback by exploiting the deep variational autoencoders (VAEs). Particularly, a two-level VAE model is built, where the first-level accounts for the joint representations while the second for the embeddings of each aspect. Extensive experiments on three real-world datasets have been conducted, and the results demonstrate the superiority of the proposed method against state-of-the-art competitors.

Deep learning has achieved great successes in conventional computer vision tasks. In this paper, we exploit deep learning techniques to address the hyperspectral image classification problem. In contrast to conventional computer vision tasks that only examine the spatial context, our proposed method can exploit both spatial context and spectral correlation to enhance hyperspectral image classification. In particular, we advocate four new deep learning models, namely, 2-D convolutional neural network (2-D-CNN), 3-D-CNN, recurrent 2-D CNN (R-2-D-CNN), and recurrent 3-D-CNN (R-3-D-CNN) for hyperspectral image classification. We conducted rigorous experiments based on six publicly available data sets. Through a comparative evaluation with other state-of-the-art methods, our experimental results confirm the superiority of the proposed deep learning models, especially the R-3-D-CNN and the R-2-D-CNN deep learning models.

Feature extraction is a prerequisite in many machine learning and data mining applications. As the advancement of data acquisition techniques, nowadays tensor objects are accumulated with respect to frequency or time information in a great number of fields. For instance color or hyperspectral faces in multichannel information, and human gait motion in time information are obtained. In this paper, we propose and develop a block principal component analysis (BPCA) to extract features for this kind of tensor objects. Our idea is to unfold tensor objects according to their spatial information and frequency/time information, and represent them in block matrix form. The corresponding covariance matrix for frequency/time information can be captured and used. The block eigen-decomposition of such covariance matrix is employed to seek for projection solution as features. Both reconstruction and classification problems can be solved via these projected features. Extensive experiments have been conducted on various face or gait databases to demonstrate the superiority of BPCA compared with existing methods such as PCA, (2D)2PCA, MPCA, and UMPCA in terms of effectiveness. Moreover, the proposed BPCA is competitively efficient compared to these existing methods.

k-Means algorithm has been proven an effective technique for clustering a large-scale data set. However, traditional k-means type clustering algorithms cannot effectively distinguish the discriminative capabilities of features in the clustering process. In this paper, we present a new k-means type clustering framework by extending W-k-means with an l2-norm regularization to the weights of features. Based on the framework, we propose the l2-Wkmeans algorithm by using conventional means as the centroids for clustering numerical data sets and present the l2-NOF and l2-NDM algorithms by using two different smooth modes representatives for clustering categorical data sets. At first, a new objective function is developed for the clustering framework. Then, the corresponding updating rules of the centroids, the membership matrix, and the weights of the features, are derived theoretically for the new algorithms. We conduct extensive experimental verifications to evaluate the performances of our proposed algorithms on numerical data sets and categorical data sets. Experimental studies demonstrate that our proposed algorithms delivers consistently promising results in comparison to the other comparative approaches, such basic k-means, W-k-means, MKM_NOF, MKM_NDM etc., with respects to four metrics: Accuracy, RandIndex, Fscore, and Normal Mutual Information (NMI).

The real-world networking data may contain different types of attribute views and relational view. Hence, it is desirable to collectively use available attribute views and relational view in order to build effective learning models. We call this framework multi-attribute and relational learning. Collective classification is one of the popular approaches that can handle both attribute and relational information for network data. However, in collective classification only one type of attribute and relational view is involved and little attention is received for multi-attribute and relational learning. In this paper, we propose a new semi-supervised collective classification approach, called hypergraph regularized generative model (HRGM), for multi-attribute and relational learning. In the approach, a generative model based on the Probabilistic Latent Semantic Analysis (PLSA) method is developed to leverage attribute information, and a hypergraph regularizer is incorporated to effectively exploit higher-order relational information among the data samples. Experimental results on various data sets have demonstrated the effectiveness of the proposed HRGM, and revealed that our approach outperforms existing collective classification methods and multi-view classification methods in terms of accuracy.

Sentiment analysis is an important but challenging task. Remarkable success has been achieved on domains where sufficient labeled training data is available. Nevertheless, annotating sufficient data is labor-intensive and time-consuming, establishing significant barriers for adapting the sentiment classification systems to new domains. In this paper, we introduce a Capsule network for sentiment analysis in domain adaptation scenario with semantic rules (CapsuleDAR). CapsuleDAR exploits capsule network to encode the intrinsic spatial part-whole relationship constituting domain invariant knowledge that bridges the knowledge gap between the source and target domains. Furthermore, we also propose a rule network to incorporate the semantic rules into the capsule network to enhance the comprehensive sentence representation learning. Extensive experiments are conducted to evaluate the effectiveness of the proposed CapsuleDAR model on a real world data set of four domains. Experimental results demonstrate that CapsuleDAR achieves substantially better performance than the strong competitors for the cross-domain sentiment classification task.

Learning object detection models from weakly labeled data is an important topic in computer vision. Among various types of weak annotations, image-level object labeling is a natural one that tells the existence, but not the precise locations, of object instances in images. Learning object detectors from image-level labels can be naturally cast as a multiple instance learning (MIL) problem. Existing MIL approaches for object detection still suffer from high false positive rates due to the lack of advanced instances selection techniques. In this study, a subspace-based generative model is proposed to select positive instances by minimizing rank of the coefficient matrix associated with the subspace models. An incoherence term between the subspace model and some “hard” negative instances in then modeled by an $\epsilon$ -insensitive loss function. To further improve the discriminative ability, an ensemble strategy is proposed by employing multiple subspace models. Rigorous experiments are performed on several datasets, and the promising experimental results demonstrate that the proposed approach is superior to the state-of-the-art weakly supervised learning algorithms in terms of precision, recall, and F -score.

Recently, due to the advancement of acquisition techniques, visual tensor data have been accumulated in a great variety of engineering fields, e.g., biometrics, neuroscience, surveillance and remote sensing. How to analyze and learn with such tensor objects thus becomes an important and growing interest in machine learning community. In this paper, we propose a block linear discriminant analysis (BLDA) algorithm to extract features for visual tensor objects such as multichannel/hyperspectral face images or human gait videos. Taking the inherent characteristic of such tensor data into account, we unfold tensor objects according to their spatial information and frequency/time information, and represent them in a block matrix form. As a result, the block form between-class and within-class scatter matrices are constructed, and a related block eigen-decomposition is solved to extract features for classification. Comprehensive experiments have been carried out to test the effectiveness of the proposed method, and the results show that BLDA outperforms existing algorithms like DATER, 2DLDA, GTDA, UMLDA, STDA and MPCA for visual tensor object analysis.

With the advancement of data acquisition techniques, tensor (multidimensional data) objects are increasingly accumulated and generated, for example, multichannel electroencephalographies, multiview images, and videos. In these applications, the tensor objects are usually nonnegative, since the physical signals are recorded. As the dimensionality of tensor objects is often very high, a dimension reduction technique becomes an important research topic of tensor data. From the perspective of geometry, high-dimensional objects often reside in a low-dimensional submanifold of the ambient space. In this paper, we propose a new approach to perform the dimension reduction for nonnegative tensor objects. Our idea is to use nonnegative Tucker decomposition (NTD) to obtain a set of core tensors of smaller sizes by finding a common set of projection matrices for tensor objects. To preserve geometric information in tensor data, we employ a manifold regularization term for the core tensors constructed in the Tucker decomposition. An algorithm called manifold regularization NTD (MR-NTD) is developed to solve the common projection matrices and core tensors in an alternating least squares manner. The convergence of the proposed algorithm is shown, and the computational complexity of the proposed method scales linearly with respect to the number of tensor objects and the size of the tensor objects, respectively. These theoretical results show that the proposed algorithm can be efficient. Extensive experimental results have been provided to further demonstrate the effectiveness and efficiency of the proposed MR-NTD algorithm.

Topic models, such as probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA), have shown impressive success in many fields. Recently, multi-view learning via probabilistic latent semantic analysis (MVPLSA), is also designed for multi-view topic modeling. These approaches are instances of generative model, whereas they all ignore the manifold structure of data distribution, which is generally useful for preserving the nonlinear information. In this paper, we propose a novel multiple graph regularized generative model to exploit the manifold structure in multiple views. Specifically, we construct a nearest neighbor graph for each view to encode its corresponding manifold information. A multiple graph ensemble regularization framework is proposed to learn the optimal intrinsic manifold. Then, the manifold regularization term is incorporated into a multi-view topic model, resulting in a unified objective function. The solutions are derived based on the Expectation Maximization optimization framework. Experimental results on real-world multi-view data sets demonstrate the effectiveness of our approach.

Time-stamped data are ubiquitous in our daily life, such as twitter data, academic papers and sensor data. Finding clusters and their evolutionary trends in time-stamped data sets are receiving increasing attention from researchers. Most existing methods, however, can only tackle the clustering problem of a data set without time-stamped information which is inherent in almost all the data objects. Actually, not only the performance can be improved by effectively incorporating the time-stamped information in the clustering process on most data sets, but also we can find the evolutionary trends of the clusters with time information. In this paper, we introduce an approach for clustering time-stamped data and discovering the evolutionary trends of the clusters by using Multiple Nonnegative Matrices Factorization (MNMF) with smooth constraint over time. To utilize time-stamped information in the clustering process, an extra object-time matrix is constructed in our proposed method. Then, we jointly factorize multiple feature matrices using smooth constraint to perform the object-time matrix to obtain the clusters and their evolutionary trends. Experimental results on real data sets demonstrate that our proposed approach outperforms the comparative algorithms with respect to Fscore, NMI or Entropy.