In recent years, single-domain generalization(SDG) fault diagnosis has become a prominent research focus in intelligent fault diagnosis due to its ability to generalize to previously unseen target domains based solely on a single source domain. The primary aim of domain generalization is to identify the intrinsic invariances underlying diverse data distributions, which have been found to be closely related to causality. While most existing fault diagnosis methods based on causal inference emphasize the invariance of causal features across domains, this study considers a stronger form of stability—namely, the cross domain consistency of features’ causal contributions to fault labels. Accordingly, a novel fault diagnosis method is proposed, which integrates Multi-scale Style Enhancement (MSSE) with Causal Contribution Alignment (CCA) to achieve SDG. First, to make up for the lack of data diversity in the source domain, domain shifts are simulated and diverse pseudo-domain samples are generated using a MSSE module. Second, causal contributions of features to diagnostic labels are quantified through causal attribution. Finally, the alignment of causal contributions of features between source and pseudo domains is enforced through contrastive learning and domain adversarial training, thereby promoting stable and cross domain invariant causal representations. Comprehensive experimental evaluations on two benchmark datasets verify that the proposed method consistently outperforms existing fault diagnosis approaches.

Abstract Currently, it is a challenging problem to make clustering algorithms suitable for arbitrary distributions of data. In this paper, we propose a Micro-cluster Structure Clustering algorithm based on the Weight-constrained Minimum Spanning Tree, called MSC-WMST. Firstly, the original data is standardized and rescaled, where each feature dimension is partitioned into several intervals by a unit length. Specified regions are separated within these intervals based on a given threshold, and data is sampled in these regions. Secondly, an improved weighted-constrained minimum spanning tree is proposed to search for initial micro-clusters from the sampled data. Thirdly, the merging indicator is jointly defined by the local density of micro-clusters and the distance between micro-clusters, and the pairs of micro-clusters that satisfy the maximum merging indicator will be iteratively merged in a bottom-up hierarchical manner to obtain the final cluster structure. In addition, noisy data can be identified by analyzing the characteristics of the minimum spanning tree. Finally, the remaining samples are assigned to the cluster nearest to them. Extensive experiments were conducted on twenty-four datasets, we compared the MSC-WMST algorithm with the state-of-the-art algorithms. The experimental results demonstrate that MSC-WMST exhibits excellent performance in three evaluation metrics.

With the evolution of information technology and media, the environment and carriers of fake news have undergone significant changes compared to the past, enabling the fabrication of user identities, social contexts of news, and other information. This poses a substantial challenge to traditional fake news detection techniques based on news content and user attributes. Consequently, researchers have explored methods utilizing the social context features of news for fake news detection. However, most approaches relying on propagation structures for detection employ only a single propagation feature, neglecting the importance of user feedback features for the global propagation structure. Additionally, the credibility of news publishers serves as critical prior information for assessing news authenticity, particularly in early detection stages. To address these limitations, this paper proposes a novel method that integrates the global propagation structure features of news with publisher credibility to capture discriminative information between real and fake news at an early propagation stage. Specifically, the method first designs a top-down forward propagation graph and a bottom-up reverse diffusion graph, using bidirectional graph convolutional networks to extract propagation features and feedback features, respectively, which are then aggregated into global structural features. Next, a structure-aware multi-head attention network is employed to predict publisher credibility, jointly optimizing the early fake news detection task. To validate the effectiveness of the proposed method, experiments are conducted on two public datasets. The results demonstrate that the proposed method outperforms existing approaches in accuracy, recall, and F1-score metrics. The code and data are available at https://github.com/dalianly/GSPC-master.

Multilingual document clustering (MDC) aims to partition multilingual documents into distinct clusters based on topic categories in an unsupervised manner. However, existing MDC methods still suffer from several limitations in practice tasks. Firstly, most of them optimize multiple objectives within the same feature space, thereby leading to the conflict between learning consistently shared semantics and reconstructing inconsistent view-specific information. Secondly, several methods directly integrate information from multilingual documents during the fusion stage, thereby overlooking the semantic differences between different language features. To address the aforementioned problems, we propose a novel multi-view learning method, called Semantic Feature Graph Consistency with Contrastive Cluster Assignments (SFGC 3 A), for MDC. Specifically, the proposed SFGC 3 A method implements consistency objective and reconstruction objective in different feature spaces, thus effectively avoiding conflicts between consistency learning and inconsistency reconstruction. Subsequently, we design the semantic feature graph consistency and semantic label consistency modules to further explore consistent semantic information among multilingual documents, thereby reducing the semantic differences among different language views. Extensive experiments on several multilingual document datasets have shown the effectiveness of the proposed SFGC 3 A method in MDC tasks. The source codes for this work will be released later.

Recently, advances in single-cell sequencing (scRNAseq) technology have enabled large-scale transcriptome analysis with high efficiency and single-cell resolution. Clustering in scRNA-seq is crucial for revealing and categorizing new cell types and gene expression patterns. However, accurate cell clustering remains a challenge due to the high dimensionality and complexity of scRNA-seq data. To overcome this challenge, in this paper, we propose a novel deep scRNA-seq clustering framework, called sparse autoencoders with gene graph embedding (scSAG2E). In our scSAG2E method, two autoencoders are firstly used to learn the low-dimensional representation of cells and genes, respectively, and the gene expression matrix of cells is reconstructed by matrix multiplication. To preserve the manifold structure of cells, we incorporate graph regularization into the cell autoencoder. Additionally, we impose sparse constraints to address the sparsity of the gene expression matrix effectively. Meanwhile, we construct the gene graph using the KNN algorithm and then feed it into the graph convolution networks (GCNs). Therefore, it effectively captures the underlying structure among genes and enhances the signal of differentially expressed genes, leading to a more accurate representation of scRNA-seq data. Extensive experimental results on several publicly available scRNA-seq datasets show that the proposed scSAG2E method outperforms several state-of-the-art single-cell analysis methods in clustering tasks. The source code for this work has been released on https://github.com/xm0312/SCAG2E

Visual Semantic Embedding ( VSE ) is a primary model for cross-modal retrieval, wherein the global feature aggregator is a crucial component of the VSE model. In recent research, the General Pooling Operator ( GPO ) aggregator, which weighs the features reconstructed from the local feature set to aggregate, facilitates the related models to achieve good retrieval performance. However, the reason for the effectiveness remains to be explored. To enhance the rationality of aggregator designs, we analyze the reason from the perspective of feature space. Indeed, for each data, the local feature set forms a hypercube containing abundant data information, and the feature learned by GPO measures the hypercube, thereby representing the data. The geometric structure of the hypercube implies that the set containing all points within the hypercube is a convex set, so the feature learned by weighted aggregation is an interior point of the hypercube. However, using the interior point to measure the hypercube leads to some problems in feature representation and model optimization, as well as the reduction of retrieval efficiency caused by weight computation. For example, the related pair’s features may be far, while the unrelated ones may be close. To measure the hypercube more clearly and alleviate the problems mentioned above, we propose Hypercube Pooling ( HCP ) aggregator. Specifically, HCP concatenates the Max and Min Pooling features as the global features. This aggregation method has multiple advantages, e.g., the learned global feature represents all hyperplanes of the hypercube that contain critical information and hypercube geometric structure. Moreover, HCP adds normalization-before-concatenation and reduces the usual setting of margin in the loss function by half to avoid gradient loss caused by the difference in the feature value and dimensionality doubling. The experimental results on the Flickr30K and MSCOCO datasets show that the HCP model has excellent performance with high efficiency, confirming the correctness of the spatial analysis and the effectiveness of the HCP aggregator.

The smallest semantic unit of the Burmese language is called the syllable. In the present study, it is intended to propose the first neural joint learning model for Burmese syllable segmentation, word segmentation, and part-of-speech ( POS ) tagging with the BERT. The proposed model alleviates the error propagation problem of the syllable segmentation. More specifically, it extends the neural joint model for Vietnamese word segmentation, POS tagging, and dependency parsing [28] with the pre-training method of the Burmese character, syllable, and word embedding with BiLSTM-CRF-based neural layers. In order to evaluate the performance of the proposed model, experiments are carried out on Burmese benchmark datasets, and we fine-tune the model of multilingual BERT. Obtained results show that the proposed joint model can result in an excellent performance.

Burmese is an isolated language, in which the syllable is the smallest unit. Syllable segmentation methods based on matching lead to performance subject to the syllable segmentation effect. This article proposes a word segmentation method with fusion conditions of double syllable features. It combines word segmentation and segmentation of syllables into one process, thus reducing the impact of errors on the syllable segmentation of Burmese. In the first layer of the conditional random fields (CRF) model, Burmese characters as atomic features are integrated into the Burma section of the Barkis Speech Paradigm (Backus normal form) features to realize the Burma syllable sequence tags. In the second layer of the CRFs model, with the syllable marked as input, it realizes the sequence markers through building a feature template with syllables as atomic features. The experimental results show that the proposed method has a better effect compared with the method based on the matching of syllables.