Search

Finding customer groups from transaction data is very important for retail and e-commerce companies. Recently, a "Purchase Tree" data structure is proposed to compress the customer transaction data and a local PurTree spectral clustering method is proposed to cluster the customer transaction data. However, in the PurTree distance, the node weights for the children nodes of a parent node are set as equal and the differences between different nodes are not distinguished. In this paper, we propose a two-level subspace weighting spectral clustering (TSW) algorithm for customer transaction data. In the new method, a PurTree subspace metric is proposed to measure the dissimilarity between two customers represented by two purchase trees, in which a set of level weights are introduced to distinguish the importance of different tree levels and a set of sparse node weights are introduced to distinguish the importance of different tree nodes in a purchase tree. TSW learns an adaptive similarity matrix from the local distances in order to better uncover the cluster structure buried in the customer transaction data. Simultaneously, it learns a set of level weights and a set of sparse node weights in the PurTree subspace distance. An iterative optimization algorithm is proposed to optimize the proposed model. We also present an efficient method to compute a regularization parameter in TSW. TSW was compared with six clustering algorithms on ten benchmark data sets and the experimental results show the superiority of the new method.

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.

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.

Books, as a representative of lengthy documents, convey rich semantics. Traditional document modeling methods, such as bag-of-words models, have difficulty capturing such rich semantics when only considering term-frequency features. In order to explore term spatial distributions over a book, a tree-structured book representation is investigated in this paper. Moreover, an efficient learning framework, Tree2Vector, is introduced for mapping tree-structured book data into vectorial space. In particular, we present two types of locality reconstruction (LR) models: Euclidean-type and cosine-type, during the transformation process of tree structures into vectorial representations. The LR is used for modeling the reconstruction process, in which each parent node in a tree is supposed to be reconstructed by its child nodes. The prominent advantage of this Tree2Vector framework is that it solely utilizes the local information within a single book tree. In addition, extensive experimental results demonstrate that Tree2Vector is able to deliver comparable or better performance in comparison to methods that consider the information of all trees in a database globally. Experimental results also suggest that cosine-type LR consistently performs better than Euclidean-type LR in applications of book and author recommendations.

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.

The SEIR model is widely used in simulating the spread of infectious diseases. COVID-19 virus is a very severe infectious disease. Some studies leverage the SEIR or SEIRD model to simulate the spread and estimate the number of infected and recovered people as time goes on. However, these models suffer from two key deficiencies: (i) conventional SEIRD does not update its model parameters w.r.t. time; (ii) it focuses on predicting the trend, instead of the actual number of infections in the future. In this paper, we propose a cascade SEIRD model. The model learns and updates its parameters every day. Moreover, it is able to predict the number of infection cases, recovered cases and deaths. Specifically, we leverage a machine learning like approach to dynamically estimate the parameters of infection rate, incubation rate, recovery rate and death rate, which can be updated by gradient descent algorithm. Once the nature of the parameters w.r.t. time is determined, ARIMA model is adopted to characterize the dynamics of the parameters and predict their future changes. To validate the effectiveness of the proposed cascade SEIRD model, we conduct experiments on five data sets of different scales of regions (China, Hubei, Wuhan, Shenzhen, US). Experimental results show that the proposed cascade SEIRD achieves the most accurate prediction and outperforms state-of-the-art techniques.

In China, many government platforms begin to offer interfaces to each other for establishing urban service collaboration systems. However, it is expensive and tedious to migrate a successful collaboration procedure from one city to another as there are no uniform standards on API definitions. In this paper, we aim to develop a method that can match the cross-city APIs for service collaboration migration. We consider the matching task as a binary classification problem. A semantic feature engineering scheme is proposed and the matching is achieved via an XGBoost classifier. Experiments demonstrate the effectiveness of the proposed method.

Graph Convolutional Networks (GCNs) have been extensively studied in recent years. Most of existing GCN approaches are designed for the homogenous graphs with a single type of relation. However, heterogeneous graphs of multiple types of relations are also ubiquitous and there is a lack of methodologies to tackle such graphs. Some previous studies address the issue by performing conventional GCN on each single relation and then blending their results. However, as the convolutional kernels neglect the correlations across relations, the strategy is sub-optimal. In this paper, we propose the Multi-Relational Graph Convolutional Network (MR-GCN) framework by developing a novel convolution operator on multi-relational graphs. In particular, our multi-dimension convolution operator extends the graph spectral analysis into the eigen-decomposition of a Laplacian tensor. And the eigen-decomposition is formulated with a generalized tensor product, which can correspond to any unitary transform instead of limited merely to Fourier transform. We conduct comprehensive experiments on four real-world multi-relational graphs to solve the semi-supervised node classification task, and the results show the superiority of MR-GCN against the state-of-the-art competitors.

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.

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).

Opportunistic mobile social network (OMSN) enables users to form an instant social network for information sharing (e.g., people watching the same soccer game can share their instant comments). OMSN is ad hoc in nature, thus relies on the cooperation of members regarding message transmission. However, some uncooperative or malicious behavior from abnormal members may reduce network performance, even damage the entire network. Currently, there does not exist effective mechanisms to detect selfish and malicious nodes. To tackle this problem, we propose a dynamic trust framework to facilitate a node to derive a trust value of another node based on the behavior of the latter. The novelty of our framework includes the following: 1) we design a new metric for a trust value of a node and 2) we propose a “two–hop feedback method” that requires intermediate nodes in a forwarding path to generate ACK messages to verify a node’s honesty if they are two hops away. In most existing trust models, final ACK messages are considered as critical factors. In OMSN, nodes are not fully connected and final ACK messages cannot be reliably received. In order to avoid the problem that few final ACK messages can be received, we propose a “two–hop feedback method.” Simulation results show that our approach is able to detect a majority of abnormal nodes including malicious nodes, selfish nodes, and those nodes launching conspiracy attacks. Thus, the entire network efficiency can be improved without negative impact of abnormal nodes. Besides, our trust framework can be easily applied to the current popular routing protocols of opportunistic networks.

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.

Existing clustering algorithms are weak in extracting smooth subspaces for clustering time series data. In this paper, we propose a new k-means type smooth subspace clustering algorithm named Time Series k-means (TSkmeans) for clustering time series data. The proposed TSkmeans algorithm can effectively exploit inherent subspace information of a time series data set to enhance clustering performance. More specifically, the smooth subspaces are represented by weighted time stamps which indicate the relative discriminative power of these time stamps for clustering objects. The main contributions of our work include the design of a new objective function to guide the clustering of time series data and the development of novel updating rules for iterative cluster searching with respect to smooth subspaces. Based on a synthetic data set and five real-life data sets, our experimental results confirm that the proposed TSkmeans algorithm outperforms other state-of-the-art time series clustering algorithms in terms of common performance metrics such as Accuracy, Fscore, RandIndex, and Normal Mutual Information.

In this paper, we make a comparative study to examine the performance of different machine learning approaches for the thunderstorm gale identification. To this end, a thunderstorm gale benchmark dataset is constructed, which comprises radar images in Guangdong from 2015 to 2017. The corresponding wind velocities recorded by the automatic meteorological observation stations are utilized to offer the ground-truth. Based on the dataset, we evaluate the performance of Decision Tree Regressor (DT), Linear Regression (LR), Ridge regression, Lasso regression, Random Forest Regressor (RFR), K-nearest Neighbor Regressor (KNNR), Bayesian Ridge Regressor (BR), Adaboost Regressor (AR), Support Vector Regressor (SVR), Gradient Boosting Regressor (GBR), and Convolutional Neural Network (CNN). Ten important features are extracted to apply these approaches, except CNN, which include radar echo intensity, radar reflectivity factor, radar combined reflectivity, vertical integrated liquid, echo tops and their changes with respect to (w.r.t.) time. Experimental results demonstrate the machine learning approaches can effectively identify the thunderstorm gale, and the CNN model performs the best. Finally, a thunderstorm system is developed based on CNN model, which help meteorologists to identify thunderstorm gales in terms of radar images.

Building personalized task-oriented dialogue system is an important but challenging task. Significant success has been achieved by selecting the responses from the pre-defined template. However, preparing massive response template is time-consuming and human-labor intensive. In this paper, we propose an end-to-end framework based on the memory networks for responses generation in the personalized task-oriented dialog system. The static attention mechanism is used to encode the user-conversation relationship to form a global vector representation, and the dynamic attention mechanism is used to obtain import local information during the decoding phase. In addition, we propose a gating mechanism to incorporate user information into the network to enhance the personalized ability of the response. Experiments on the benchmark dataset show that our model achieves better performance than the strong baseline methods in personalized task-oriented dialogue generation.

Integrative analysis of multi-omics layers at single cell level is critical for accurate dissection of cell-to-cell variation within certain cell populations. Here we report scCAT-seq, a technique for simultaneously assaying chromatin accessibility and the transcriptome within the same single cell. We show that the combined single cell signatures enable accurate construction of regulatory relationships between cis-regulatory elements and the target genes at single-cell resolution, providing a new dimension of features that helps direct discovery of regulatory patterns specific to distinct cell identities. Moreover, we generate the first single cell integrated map of chromatin accessibility and transcriptome in early embryos and demonstrate the robustness of scCAT-seq in the precise dissection of master transcription factors in cells of distinct states. The ability to obtain these two layers of omics data will help provide more accurate definitions of “single cell state” and enable the deconvolution of regulatory heterogeneity from complex cell populations., Heterogeneity in gene expression and epigenetic states exists across individual cells. Here, the authors develop scCAT-seq, a technique for simultaneously performing ATAC-seq and RNA-seq within the same single cell.

Stance classification is a natural language processing (NLP) task to detect author’s stance when give a specific target and context, which can be applied in online debating forum, e.g., Twitter, Weibo, etc. In this paper, we present a novel target orientation recurrent neural capsule network, called TRNN-Capsule to solve the problem. In TRNN-Capsule, the target and context are both encoded by leveraging a bidirectional LSTM model. Then, capsule blocks are appended to produce the final classification outcome. Experiments on two benchmark data sets are conducted and the results show that the proposed TRNN-Capsule outperforms state-of-the-art competitors for the stance classification task.

The task of precipitation nowcasting is significant in the operational weather forecast. The radar echo map extrapolation plays a vital role in this task. Recently, deep learning techniques such as Convolutional Recurrent Neural Network (ConvRNN) models have been designed to solve the task. These models, albeit performing much better than conventional optical flow based approaches, suffer from a common problem of underestimating the high echo value parts. The drawback is fatal to precipitation nowcasting, as the parts often lead to heavy rains that may cause natural disasters. In this paper, we propose a novel interaction dual attention long short-term memory (IDA-LSTM) model to address the drawback. In the method, an interaction framework is developed for the ConvRNN unit to fully exploit the short-term context information by constructing a serial of coupled convolutions on the input and hidden states. Moreover, a dual attention mechanism on channels and positions is developed to recall the forgotten information in the long term. Comprehensive experiments have been conducted on CIKM AnalytiCup 2017 data sets, and the results show the effectiveness of the IDA-LSTM in addressing the underestimation drawback. The extrapolation performance of IDA-LSTM is superior to that of the state-of-the-art methods.

Building a personalized task-oriented dialogue system is an important but challenging task. Significant success has been achieved in the template selection responses. However, preparing a massive response template is time-consuming and human-labor intensive. In this paper, we propose an end-to-end framework based on memory networks for response generation in a personalized task-oriented dialogue system. Our model consists of three parts: a retrieval module, a memory encoder network and a memory decoder network. Retrieval module employs the user utterances and user attributes to collect relevant responses from other users. Memory encoder is trained with textual features to obtain dialogue representation. Memory decoder is composed of an RNN and a rule-memory network for response generation. Experiments on the benchmark dataset show that our model achieves better performance than strong baselines in personalized task-oriented dialogue generation.

Multi-label classification addresses the problem that each instance is associated with multiple labels simultaneously. In this paper, we propose a multi-label crotch ensemble (MLCE) model for multi-label classification, which takes label correlations into consideration. In MLCE, a multi-label cluster tree is first constructed. Then, we incorporate all multi-label crotch predictors of the tree into a classifier, where the multi-label crotch predictor is the crotch formed by an inner node of the tree and its children. Finally, a flexible weighted voting scheme is designed to produce the classification output. We perform experiments on 11 benchmark datasets. Experimental results clearly demonstrate the MLCE significantly outperforms six well-established multi-label classification approaches, in terms of the widely used evaluation metrics.

Reinforcement learning techniques have recently been introduced to interactive recommender systems to capture the dynamic patterns of user behavior during the interaction with recommender systems and perform planning to optimize long-term performance. Most existing research work focuses on designing policy and learning algorithms of the recommender agent but seldom cares about the state representation of the environment, which is indeed essential for the recommendation decision making. In this paper, we first formulate the interactive recommender system problem with a deep reinforcement learning recommendation framework. Within this framework, we then carefully design four state representation schemes for learning the recommendation policy. Inspired by recent advances in feature interaction modeling in user response prediction, we discover that explicitly modeling user–item interactions in state representation can largely help the recommendation policy perform effective reinforcement learning. Extensive experiments on four real-world datasets are conducted under both the offline and simulated online evaluation settings. The experimental results demonstrate the proposed state representation schemes lead to better performance over the state-of-the-art methods.

Discovering global knowledge from distributed data sources is challenging as there exist several practical concerns such as bandwidth limitation and data privacy. By appropriately abstracting distributed data, various global data mining tasks could still be implemented on the basis of local data abstractions. This article reviews existing techniques related to distributed data mining in abstraction-based data mining. It then discusses open research challenges on mining tasks performed on distributed and abstracted data, describes how global data models clustering and manifold discovery could be learnt based on local data models, and points out future research directions. WIREs Data Mining Knowl Discov 2016, 6:167-176. doi: 10.1002/widm.1182

Multi-attribute network refers to network data with multiple attribute views and relational view. Although semi-supervised collective classification has been investigated extensively, little attention is received for such kind of network data. In this paper, we aim to study and solve the semi-supervised learning problem for multi-attribute networks. There are two important challenges: (1) how to extract effective information from the rich multi-attribute and relational information; (2) how to make use of unlabeled data in the network. We propose a new generative model with network regularization, called MARL, which addresses the two challenges. In the approach, a generative model based on the probabilistic latent semantic analysis method is developed to leverage attribute information, and a network regularizer is incorporated to smooth label probability with relational information and unlabeled data. Comprehensive experiments on various data sets have been conducted to demonstrate the effectiveness of the proposed MARL, and the results reveal that our approach outperforms existing collective classification methods and multi-view classification methods in terms of accuracy.

A new triple wing harmonium (TWH) model that integrates text metadata into a low-dimensional semantic space is proposed for the application of content-based movie recommendation. The text metadata considered here include movie synopsis, actor list, and user comments. We develop a new TWH model projecting these multiple textual features into low-dimensional latent topics with different probability distribution assumptions. A contrastive divergence (CD) algorithm is used for efficient learning and inference. Experimental results suggest that the proposed method performs better than the state-of-the-art algorithms for movie recommendation.

Conventionally, it is a prerequisite to acquire a good number of annotated data to train an accurate classifier. However, the acquisition of such dataset is usually infeasible due to the high annotation cost. Therefore, semi-supervised learning has emerged and attracts increasing research efforts in recent years. Essentially, semi-supervised learning is sensitive to the manner how the unlabeled data is sampled. However, the model performance might be seriously deteriorated if biased unlabeled data is sampled at the early stage. In this paper, an unbiased semi-supervised cluster tree is proposed which is learnt using only very few labeled data. Specifically, a K-means algorithm is adopted to build each level of this hierarchical tree in a decent top-down manner. The number of clusters is determined by the number of classes contained in the labeled data. The confidence error of the cluster tree is theoretically analyzed which is then used to prune the tree. Empirical studies on several datasets have demonstrated that the proposed semi-supervised cluster tree is superior to the state-of-the-art semi-supervised learning algorithms with respect to classification accuracy.

In this paper, a deep learning classification model is proposed for automatically detecting the marine oil spill in Lanset-7 and Lanset-8 images, which can combine fully convolutional network (FCN) with Resnet and Googlenet respectively. The classification algorithms, i.e. FCN-Googlenet and FCN-ResNet are compared to the state-of-the-art Support Vector Machine (SVM) method. The experimental results show that our FCN-Googlenet and FCN-ResNet models outperform other approaches with a significant improvement. Moreover, our methods are more flexible in that no restriction on the size of input image is required in our algorithmic setups, which is more suitable in real applications.

Actors (e.g., people, organizations and nations) of online social networks often express different opinions toward opinion targets (e.g., products, events and political figures). Extracting and visualizing the distributions of different opinions among actors facilitate policy-makers (e.g., business managers and government officials) to develop informed decisions promptly. In this paper, by extending the notion of signed networks, we first provide a formal definition of opinion networks which are networks of actors who hold potentially different opinions against specific targets. Another main contribution of our research is the development of a visualization method called OpinionRings to infer and visualize the actual and the potential opinions of different groups of actors. In particular, the proposed OpinionRings method leverages three concentric rings with various colors and widths to highlight different groups of actors and their opinions. One unique feature of the OpinionRings method is that the inclination of an actor, who originally holds a neutral opinion polarity, to adopt a positive or negative opinion polarity can be estimated according to the color of the actor and the distance to other actors with known opinion polarities. A series of objective quantitative experiments and subjective user-based evaluation show that the proposed OpinionRings method significantly outperforms the traditional visualization methods in terms of cohesiveness of displays, informativeness of visualized contents, and inference power of the visualization scheme. The practical implication of our research is that business managers or government officials can apply our proposed computational method to extract and visualize valuable social intelligence from online social networks to facilitate their decision-making processes.

In the era of the Social Web, actors (e.g. people, organizations, nations, etc) of online social media often voice out their opinions towards a variety of opinion targets. Extracting and visualizing distributions of multiple opinions among actors facilitates individuals or organizations to extract valuable social intelligence from online social media. The main contribution of our research reported in this paper is the development of a novel opinion analysis methodology named Multi-opinion Ring for visualizing and predicting multiple opinion orientations held by different groups of actors in online social media. In particular, the proposed Multi-opinion Ring method combines visualization techniques with machine learning methods to predict the opinion inclinations of actors who are originally neutral to different opinion targets. A series of controlled experiments, user-based evaluations, and case studies show that the proposed Multi-opinion Ring method significantly outperforms classical visualization methods in terms of the cohesiveness of the graphical layout and the informativeness of the visualized contents.