Flow to Candidate: Temporal Knowledge Graph Reasoning With Candidate-Oriented Relational Graph.

Reasoning over temporal knowledge graphs (TKGs) is a challenging task that requires models to infer future events based on past facts. Currently, subgraph-based methods have become the state-of-the-art (SOTA) techniques for this task due to their superior capability to explore local information in knowledge graphs (KGs). However, while previous methods have been effective in capturing semantic patterns in TKG, they are hard to capture more complex topological patterns. In contrast, path-based methods can efficiently capture relation paths between nodes and obtain relation patterns based on the order of relation connections. But subgraphs can retain much more information than a single path. Motivated by this observation, we propose a new subgraph-based approach to capture complex relational patterns. The method constructs candidate-oriented relational graphs to capture the local structure of TKGs and introduces a variant of a graph neural network model to learn the graph structure information between query-candidate pairs. In particular, we first design a prior directed temporal edge sampling method, which is starting from the query node and generating multiple candidate-oriented relational graphs simultaneously. Next, we propose a recursive propagation architecture that can encode all relational graphs in the local structures in parallel. Additionally, we introduce a self-attention mechanism in the propagation architecture to capture the query's preference. Finally, we design a simple scoring function to calculate the candidate nodes' scores and generate the model's predictions. To validate our approach, we conduct extensive experiments on four benchmark datasets (ICEWS14, ICEWS18, ICEWS0515, and YAGO). Experiments on four benchmark datasets demonstrate that our proposed approach possesses stronger inference and faster convergence than the SOTA methods. In addition, our method provides a relational graph for each query-candidate pair, which offers interpretable evidence for TKG prediction results.

Four New Species of Tomentella (Thelephorales, Basidiomycota) from Subtropical Forests in Southwestern China.

Species of the basidiomycetous genus Tomentella are widely distributed throughout temperate forests. Numerous studies on the taxonomy and phylogeny of Tomentella have been conducted from the temperate zone in the Northern hemisphere, but few have been from subtropical forests. In this study, four new species, T. casiae, T. guiyangensis, T. olivaceomarginata and T. rotundata from the subtropical mixed forests of Southwestern China, are described and illustrated based on morphological characteristics and phylogenetic analyses of the internal transcribed spacer regions (ITS) and the large subunit of the nuclear ribosomal RNA gene (LSU). Molecular analyses using Maximum Likelihood and Bayesian analysis confirmed the phylogenetic positions of these four new species. Anatomical comparisons among the closely related species in phylogenetic and morphological features are discussed. Four new species could be distinguished by the characteristics of basidiocarps, the color of the hymenophoral surface, the size of the basidia, the shape of the basidiospores and some other features.

QKSAN: A Quantum Kernel Self-Attention Network.

The Self-Attention Mechanism (SAM) excels at distilling important information from the interior of data to improve the computational efficiency of models. Nevertheless, many Quantum Machine Learning (QML) models lack the ability to distinguish the intrinsic connections of information like SAM, which limits their effectiveness on massive high-dimensional quantum data. To tackle the above issue, a Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. Further, a Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques to release half of quantum resources by mid-circuit measurement, thereby bolstering both feasibility and adaptability. Simultaneously, the Quantum Kernel Self-Attention Score (QKSAS) with an exponentially large characterization space is spawned to accommodate more information and determine the measurement conditions. Eventually, four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST, where the QKSAS tests and correlation assessments between noise immunity and learning ability are executed on the best-performing sub-model. The paramount experimental finding is that the QKSAN subclasses possess the potential learning advantage of acquiring impressive accuracies exceeding 98.05% with far fewer parameters than classical machine learning models. Predictably, QKSAN lays the foundation for future quantum computers to perform machine learning on massive amounts of data while driving advances in areas such as quantum computer vision.

GPC3-targeted CAR-M cells exhibit potent antitumor activity against hepatocellular carcinoma.

Chimeric antigen receptor (CAR)-modified macrophages are a promising treatment for solid tumor. So far the potential effects of CAR-M cell therapy have rarely been investigated in hepatocellular carcinoma (HCC). Glypican-3 (GPC3) is a biomarker for a variety of malignancies, including liver cancer, which is not expressed in most adult tissues. Thus, it is an ideal target for the treatment of HCC. In this study, we engineered mouse macrophage cells with CAR targeting GPC3 and explored its therapeutic potential in HCC. First, we generated a chimeric adenoviral vector (Ad5f35) delivering an anti-GPC3 CAR, Ad5f35-anti-GPC3-CAR, which using the CAR construct containing the scFv targeting GPC3 and CD3ζ intracellular domain. Phagocytosis and killing effect indicated that macrophages transduced with Ad5f35-anti-GPC3-CAR (GPC3 CAR-Ms) exhibited antigen-specific phagocytosis and tumor cell clearance in vitro, and GPC3 CAR-Ms showed significant tumor-killing effects and promoted expression of pro-inflammatory (M1) cytokines and chemokines. In 3D NACs-origami spheroid model of HCC, CAR-Ms were further demonstrated to have a significant tumor killing effect. Together, our study provides a new strategy for the treatment of HCC through CAR-M cells targeting GPC3, which provides a basis for the research and treatment of hepatocellular carcinoma.

Multi-input mutual supervision network for single-pixel computational imaging.

In this study, we propose a single-pixel computational imaging method based on a multi-input mutual supervision network (MIMSN). We input one-dimensional (1D) light intensity signals and two-dimensional (2D) random image signal into MIMSN, enabling the network to learn the correlation between the two signals and achieve information complementarity. The 2D signal provides spatial information to the reconstruction process, reducing the uncertainty of the reconstructed image. The mutual supervision of the reconstruction results for these two signals brings the reconstruction objective closer to the ground truth image. The 2D images generated by the MIMSN can be used as inputs for subsequent iterations, continuously merging prior information to ensure high-quality imaging at low sampling rates. The reconstruction network does not require pretraining, and 1D signals collected by a single-pixel detector serve as labels for the network, enabling high-quality image reconstruction in unfamiliar environments. Especially in scattering environments, it holds significant potential for applications.

Nonlinear Locality-Preserving Projections With Dynamic Graph Learning.

The affinity graph is regarded as a mathematical representation of the local manifold structure. The performance of locality-preserving projections (LPPs) and its variants is tied to the quality of the affinity graph. However, there are two drawbacks in current approaches. First, the pre-designed graph is inconsistent with the actual distribution of data. Second, the linear projection way would cause damage to the nonlinear manifold structure. In this article, we propose a nonlinear dimensionality reduction model, named deep locality-preserving projections (DLPPs), to solve these problems simultaneously. The model consists of two loss functions, each employing deep autoencoders (AEs) to extract discriminative features. In the first loss function, the affinity relationships among samples in the intermediate layer are determined adaptively according to the distances between samples. Since the features of samples are obtained by nonlinear mapping, the manifold structure can be kept in the low-dimensional space. Additionally, the learned affinity graph is able to avoid the influence of noisy and redundant features. In the second loss function, the affinity relationships among samples in the last layer (also called the reconstruction layer) are learned. This strategy enables denoised samples to have a good manifold structure. By integrating these two functions, our proposed model minimizes the mismatch of the manifold structure between samples in the denoising space and the low-dimensional space, while reducing sensitivity to the initial weights of the graph. Extensive experiments on toy and benchmark datasets have been conducted to verify the effectiveness of our proposed model.

Allergen Sensitization of Parents and Children With Respiratory Allergic Diseases.

OBJECTIVE: To study the differences in allergen sensitization of parents and their offspring with respiratory allergic diseases. METHODS: We included parents and their children who were both diagnosed with allergic asthma and/or allergic rhinitis, between January 2018 and December 2022. Parent-child dyads were evaluated for sensitization to six categories of allergens viz, dust mite, fungus, animal dander, weed pollen, tree pollen and food allergen, by measuring the allergen-specific immunoglobulin E levels (sIgE). Data of gender, age, feeding history, serum total IgE (tIgE), and absolute eosinophil counts (AEC) were collected and analyzed for differences in allergen sensitization of parents and children. RESULTS: Overall, the AEC in children were significantly higher than that of parents. The sensitivity to fungal allergens in children was significantly higher than that in fathers (33.3% vs 6.7%, P = 0.01) as well as mothers (29.3% vs 8.3%, P = 0.03). Sensitization to food allergens was also higher in children compared to fathers (25.4% vs 7.9%, P = 0.01). Fathers with tree pollen allergen sensitivity, and mothers with weed pollen allergen sensitivity had a significantly increased risk (aOR, 95% CI) of having increased sensitivity to these allergens in their offspring; 24.01 (1.08, 53.99; P = 0.04) and 3.27 (1.08, 9.92; P = 0.04), respectively. CONCLUSION: Children had greater sensitivity for fungal allergens compared to both parents, as well as food allergy compared to fathers. Fathers with tree pollen allergen sensitivity, and mothers with weed pollen allergen sensitivity had an increased risk of having their children sensitive to these types of allergens.

Motion-Aware Video Frame Interpolation.

Video frame interpolation methodologies endeavor to create novel frames betwixt extant ones, with the intent of augmenting the video's frame frequency. However, current methods are prone to image blurring and spurious artifacts in challenging scenarios involving occlusions and discontinuous motion. Moreover, they typically rely on optical flow estimation, which adds complexity to modeling and computational costs. To address these issues, we introduce a Motion-Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames by introducing a novel hierarchical pyramid module. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, enabling the model to capture intricate motion patterns, but also effectively reduces the required computational cost and complexity. Subsequently, a cross-scale motion structure is presented to estimate and refine intermediate flow maps by the extracted features. This approach facilitates the interplay between input frame features and flow maps during the frame interpolation process and markedly heightens the precision of the intervening flow delineations. Finally, a discerningly fashioned loss centered around an intermediate flow is meticulously contrived, serving as a deft rudder to skillfully guide the prognostication of said intermediate flow, thereby substantially refining the precision of the intervening flow mappings. Experiments illustrate that MA-VFI surpasses several representative VFI methods across various datasets, and can enhance efficiency while maintaining commendable efficacy.

Misclassification in Weakly Supervised Object Detection.

Weakly supervised object detection (WSOD) aims to train detectors using only image-category labels. Current methods typically first generate dense class-agnostic proposals and then select objects based on the classification scores of these proposals. These methods mainly focus on selecting the proposal having high Intersection-over-Union with the true object location, while ignoring the problem of misclassification, which occurs when some proposals exhibit semantic similarities with objects from other categories due to viewing perspective and background interference. We observe that the positive class that is misclassified typically has the following two characteristics: 1) It is usually misclassified as one or a few specific negative classes, and the scores of these negative classes are high; 2) Compared to other negative classes, the score of the positive class is relatively high. Based on these two characteristics, we propose misclassification correction (MCC) and misclassification tolerance (MCT) respectively. In MCC, we establish a misclassification memory bank to record and summarize the class-pairs with high frequencies of potential misclassifications in the early stage of training, that is, cases where the score of a negative class is significantly higher than that of the positive class. In the later stage of training, when such cases occur and correspond to the summarized class-pairs, we select the top-scoring negative class proposal as the positive training example. In MCT, we decrease the loss weights of misclassified classes in the later stage of training to avoid them dominating training and causing misclassification of objects from other classes that are semantically similar to them during inference. Extensive experiments on the PASCAL VOC and MS COCO demonstrate our method can alleviate the problem of misclassification and achieve the state-of-the-art results.

In situ construction of A-site high-entropy perovskites with interfacial CeO2 for a high-performance IT-SOFC air-electrode.

Developing an intermediate-temperature solid oxide fuel cell (IT-SOFC) is one of the most promising ways of achieving carbon neutrality, but its air-electrode is restricted by the conflict between the sluggish catalytic activity and durability. Herein, an A-site high-entropy perovskite composite La0.2Ba0.2Sr0.2Ca0.2Ce0.2-xCoO3-δ-xCeO2 (LBSCCC-CeO2) air-electrode material is fabricated via a one-step self-constructing strategy, which shows excellent oxygen reduction activity and stability due to the high-entropy structure and the synergy effect between LBSCCC and interfacial CeO2. This work provides a new way of fabricating high-performance air-electrodes in IT-SOFCs.

Pretrained Quantum-Inspired Deep Neural Network for Natural Language Processing.

Natural language processing (NLP) may face the inexplicable "black-box" problem of parameters and unreasonable modeling for lack of embedding of some characteristics of natural language, while the quantum-inspired models based on quantum theory may provide a potential solution. However, the essential prior knowledge and pretrained text features are often ignored at the early stage of the development of quantum-inspired models. To attacking the above challenges, a pretrained quantum-inspired deep neural network is proposed in this work, which is constructed based on quantum theory for carrying out strong performance and great interpretability in related NLP fields. Concretely, a quantum-inspired pretrained feature embedding (QPFE) method is first developed to model superposition states for words to embed more textual features. Then, a QPFE-ERNIE model is designed by merging the semantic features learned from the prevalent pretrained model ERNIE, which is verified with two NLP downstream tasks: 1) sentiment classification and 2) word sense disambiguation (WSD). In addition, schematic quantum circuit diagrams are provided, which has potential impetus for the future realization of quantum NLP with quantum device. Finally, the experiment results demonstrate QPFE-ERNIE is significantly better for sentiment classification than gated recurrent unit (GRU), BiLSTM, and TextCNN on five datasets in all metrics and achieves better results than ERNIE in accuracy, F1-score, and precision on two datasets (CR and SST), and it also has advantage for WSD over the classical models, including BERT (improves F1-score by 5.2 on average) and ERNIE (improves F1-score by 4.2 on average) and improves the F1-score by 8.7 on average compared with a previous quantum-inspired model QWSD. QPFE-ERNIE provides a novel pretrained quantum-inspired model for solving NLP problems, and it lays a foundation for exploring more quantum-inspired models in the future.

Joint Structured Bipartite Graph and Row-Sparse Projection for Large-Scale Feature Selection.

Feature selection plays an important role in data analysis, yet traditional graph-based methods often produce suboptimal results. These methods typically follow a two-stage process: constructing a graph with data-to-data affinities or a bipartite graph with data-to-anchor affinities and independently selecting features based on their scores. In this article, a large-scale feature selection approach based on structured bipartite graph and row-sparse projection (RS 2 BLFS) is proposed to overcome this limitation. RS 2 BLFS integrates the construction of a structured bipartite graph consisting of c connected components into row-sparse projection learning with k nonzero rows. This integration allows for the joint selection of an optimal feature subset in an unsupervised manner. Notably, the c connected components of the structured bipartite graph correspond to c clusters, each with multiple subcluster centers. This feature makes RS 2 BLFS particularly effective for feature selection and clustering on nonspherical large-scale data. An algorithm with theoretical analysis is developed to solve the optimization problem involved in RS 2 BLFS. Experimental results on synthetic and real-world datasets confirm its effectiveness in feature selection tasks.

Image Reconstruction for Accelerated MR Scan With Faster Fourier Convolutional Neural Networks.

High quality image reconstruction from undersampled k -space data is key to accelerating MR scanning. Current deep learning methods are limited by the small receptive fields in reconstruction networks, which restrict the exploitation of long-range information, and impede the mitigation of full-image artifacts, particularly in 3D reconstruction tasks. Additionally, the substantial computational demands of 3D reconstruction considerably hinder advancements in related fields. To tackle these challenges, we propose the following: 1) A novel convolution operator named Faster Fourier Convolution (FasterFC), aims at providing an adaptable broad receptive field for spatial domain reconstruction networks with fast computational speed. 2) A split-slice strategy that substantially reduces the computational load of 3D reconstruction, enabling high-resolution, multi-coil, 3D MR image reconstruction while fully utilizing inter-layer and intra-layer information. 3) A single-to-group algorithm that efficiently utilizes scan-specific and data-driven priors to enhance k -space interpolation effects. 4) A multi-stage, multi-coil, 3D fast MRI method, called the faster Fourier convolution based single-to-group network (FAS-Net), comprising a single-to-group k -space interpolation algorithm and a FasterFC-based image domain reconstruction module, significantly minimizes the computational demands of 3D reconstruction through split-slice strategy. Experimental evaluations conducted on the NYU fastMRI and Stanford MRI Data datasets reveal that the FasterFC significantly enhances the quality of both 2D and 3D reconstruction results. Moreover, FAS-Net, characterized as a method that can achieve high-resolution (320, 320, 256), multi-coil, (8 coils), 3D fast MRI, exhibits superior reconstruction performance compared to other state-of-the-art 2D and 3D methods.

Genome-wide identification and analysis of DEAD-box RNA helicases in Gossypium hirsutum.

DEAD-box RNA helicases, a prominent subfamily within the RNA helicase superfamily 2 (SF2), play crucial roles in the growth, development, and abiotic stress responses of plants. This study identifies 146 DEAD-box RNA helicase genes (GhDEADs) and categorizes them into four Clades (Clade A-D) through phylogenetic analysis. Promoter analysis reveals cis-acting elements linked to plant responses to light, methyl jasmonate (MeJA), abscisic acid (ABA), low temperature, and drought. RNA-seq data demonstrate that Clade C GhDEADs exhibit elevated and ubiquitous expression across different tissues, validating their connection to leaf development through real-time quantitative polymerase chain reaction (RT-qPCR) analysis. Notably, over half of GhDEADs display up-regulation in the leaves of virus-induced gene silencing (VIGS) plants of GhVIR-A/D (members of m6A methyltransferase complex, which regulate leaf morphogenesis). In conclusion, this study offers a comprehensive insight into GhDEADs, emphasizing their potential involvement in leaf development.

Serum phosphorus concentration and its association with the degree and pattern of intracranial arterial calcification.

BACKGROUND AND AIM: The aim of this study was to determine whether the serum phosphorus concentrations (SPC) are associated with the degree and pattern of intracranial arterial calcification (IAC) in patients with normal renal function or mild-moderate renal impairment. METHODS AND RESULTS: A total of 513 patients were enrolled in this study. The degree of IAC measured by IAC scores was evaluated on non-contrast head computed tomography (CT) images and IAC was classified as intimal or medial calcification. Study participants were classified according to IAC degrees (mild, moderate and severe) and patterns (intimal and medial calcification). A multivariate regression model was used to assess the independent relationship of SPC with IAC scores and patterns. Of 513 study participants (mean [SD] age, 68.3 [10.3] years; 246 females [48%]), the mean SPC was 1.07 ± 0.17 mmol/L and IAC scores was 4.0 (3.0-5.0). Multivariate analysis showed that higher serum phosphorus was a significant risk factor for moderate/severe IAC in both patients with eGFR ≥60 ml/min/1.73 m2 (odds ratio [OR], 1.27; 95% confidence interval [CI], 1.01-1.59; P < 0.05) and eGFR <60 ml/min/1.73 m2 (OR, 1.92; 95% CI, 1.04-3.57; P < 0.05), when those with mild IAC were considered as the reference group. However, higher SPC was associated with an increased odds of medial calcification only in patients with eGFR <60 ml/min/1.73 m2 (OR, 1.67; 95% CI, 1.08 to 2.61). CONCLUSIONS: High levels of serum phosphorus were positively correlated with the degree of IAC, and this significant effect on medial IAC was only present in patients with impaired renal function (eGFR <60 ml/min/1.73 m2).

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One.

Graph neural networks (GNN) suffer from severe inefficiency due to the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT) and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity. To avoid the only unidirectional information delivery of FT and sufficiently train shallow modules with the deeper ones, we develop a backward training mechanism that makes the former modules perceive the latter modules, inspired by the classical backward propagation algorithm. The backward training introduces the reversed information delivery into the decoupled modules as well as the forward information delivery. To investigate how the decoupling and greedy training affect the representational capacity, we theoretically prove that the error produced by linear modules will not accumulate on unsupervised tasks in most cases. The theoretical and experimental results show that the proposed framework is highly efficient with reasonable performance, which may deserve more investigation.

RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging.

Deep unrolling-based snapshot compressive imaging (SCI) methods, which employ iterative formulas to construct interpretable iterative frameworks and embedded learnable modules, have achieved remarkable success in reconstructing 3-dimensional (3D) hyperspectral images (HSIs) from 2D measurement induced by coded aperture snapshot spectral imaging (CASSI). However, the existing deep unrolling-based methods are limited by the residuals associated with Taylor approximations and the poor representation ability of single hand-craft priors. To address these issues, we propose a novel HSI construction method named residual completion unrolling with mixed priors (RCUMP). RCUMP exploits a residual completion branch to solve the residual problem and incorporates mixed priors composed of a novel deep sparse prior and mask prior to enhance the representation ability. Our proposed CNN-based model can significantly reduce memory cost, which is an obvious improvement over previous CNN methods, and achieves better performance compared with the state-of-the-art transformer and RNN methods. In this work, our method is compared with the 9 most recent baselines on 10 scenes. The results show that our method consistently outperforms all the other methods while decreasing memory consumption by up to 80%.

Parameter-Free Multiview K -Means Clustering With Coordinate Descent Method.

Recently, more and more real-world datasets have been composed of heterogeneous but related features from diverse views. Multiview clustering provides a promising attempt at a solution for partitioning such data according to heterogeneous information. However, most existing methods suffer from hyper-parameter tuning trouble and high computational cost. Besides, there is still an opportunity for improvement in clustering performance. To this end, a novel multiview framework, called parameter-free multiview k -means clustering with coordinate descent method (PFMVKM), is presented to address the above problems. Specifically, PFMVKM is completely parameter-free and learns the weights via a self-weighted scheme, which can avoid the intractable process of hyper-parameters tuning. Moreover, our model is capable of directly calculating the cluster indicator matrix, with no need to learn the cluster centroid matrix and the indicator matrix simultaneously as previous multiview methods have to do. What's more, we propose an efficient optimization algorithm utilizing the idea of coordinate descent, which can not only reduce the computational complexity but also improve the clustering performance. Extensive experiments on various types of real datasets illustrate that the proposed method outperforms existing state-of-the-art competitors and conforms well with the actual situation.

Parameter-Insensitive Min Cut Clustering With Flexible Size Constrains.

Clustering is a fundamental topic in machine learning and various methods are proposed, in which K-Means (KM) and min cut clustering are typical ones. However, they may produce empty or skewed clustering results, which are not as expected. In KM, the constrained clustering methods have been fully studied while in min cut clustering, it still needs to be developed. In this paper, we propose a parameter-insensitive min cut clustering with flexible size constraints. Specifically, we add lower limitations on the number of samples for each cluster, which can perfectly avoid the trivial solution in min cut clustering. As far as we are concerned, this is the first attempt of directly incorporating size constraints into min cut. However, it is a NP-hard problem and difficult to solve. Thus, the upper limits is also added in but it is still difficult to solve. Therefore, an additional variable that is equivalent to label matrix is introduced in and the augmented Lagrangian multiplier (ALM) is used to decouple the constraints. In the experiments, we find that the our algorithm is less sensitive to lower bound and is practical in image segmentation. A large number of experiments demonstrate the effectiveness of our proposed algorithm.

A Revised Formation of Trace Ratio LDA for Small Sample Size Problem.

Linear discriminant analysis (LDA) is a classic tool for supervised dimensionality reduction. Because the projected samples can be classified effectively, LDA has been successfully applied in many applications. Among the variants of LDA, trace ratio LDA (TR-LDA) is a classic form due to its explicit meaning. Unfortunately, when the sample size is much smaller than the data dimension, the algorithm for solving TR-LDA does not converge. The so-called small sample size (SSS) problem severely limits the application of TR-LDA. To solve this problem, we propose a revised formation of TR-LDA, which can be applied to datasets with different sizes in a unified form. Then, we present an optimization algorithm to solve the proposed method, explain why it can avoid the SSS problem, and analyze the convergence and computational complexity of the optimization algorithm. Next, based on the introduced theorems, we quantitatively elaborate on when the SSS problem will occur in TR-LDA. Finally, the experimental results on real-world datasets demonstrate the effectiveness of the proposed method.