Lifelong model editing aims to dynamically adjust a model's output concerning specific facts, knowledge items, or behaviors, enabling the model to adapt to the evolving demands of realworld applications.While some retrieval-based methods have demonstrated potential in lifelong editing scenarios by storing edited knowledge in external memory, they often suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits.To address these issues, we propose a plug-and-play method for knowledge retrieval and injection, i.e., Layer-Level Prompting (LLP), which enables seamless and efficient lifelong model editing.In our LLP framework, the reasoning process of LLMs is divided into two stages, respectively, knowledge retrieval (Thinking) and knowledge injection (Recalling).Specifically, the knowledge retrieval process is performed in the early layers of the model, using layer outputs as thinking clues.And access the updated knowledge from memory in the subsequent layer to complete the knowledge injection process.Experimental results demonstrate that our method consistently outperforms existing techniques on lifelong model editing tasks, achieving superior performance on question answering and hallucination benchmarks across different LLMs.

Multivariate time series (MTS) classification has attracted increasing attention across various domains. Existing methods either decompose MTS into separate univariate series, ignoring inter-variable dependencies, or jointly model all variables, which may lead to over-smoothing and loss of semantic structure. These limitations become particularly pronounced when dealing with complex and heterogeneous variable types. To address these challenges, we propose SwinGroupNet (SGN), which explores a novel perspective for constructing variable interaction and temporal dependency. Specifically, SGN processes multi-scale time series using (1) Variable Group Embedding (VGE), which partitions variables into groups and performs independent group-wise embedding; (2) Multi-Scale Group Window Mixing (MGWM), which reconstructs variable interactions by modeling both intra-group and inter-group dependencies while extracting multi-scale temporal features; and (3) Periodic Window Shifting and Merging (PWSM), which exploits inherent periodic patterns to enable hierarchical temporal interaction and feature aggregation. Extensive experiments on diverse benchmark datasets from multiple domains demonstrate that SGN consistently achieves state-of-the-art performance, with an average improvement of 4.2% over existing methods. We release the source code at https://anonymous.4open.science/r/SGN.

The advancement of deep clustering in recent years has been propelled by advances in deep learning technology, breaking through bottlenecks and being widely applied in multiple fields. However, current deep clustering algorithms focus only on single information or cannot fully balance the interrelationships between the original architecture and underlying institutions. Therefore, we propose a new method called structural embedding contrastive graph clustering (SECGC) that can effectively address the aforementioned issues. Firstly, We capture deeper representational information through higher-order neighborhood information models. Secondly, we designed an attribute structure fusion module that adaptively integrates the obtained high-order neighborhood information with the attribute information of the autoencoder. Simultaneously, the multi-scale feature fusion module fuses information from different dimensions to explor varying levels of semantic hierarchy. In addition, a dual self-supervised mechanism and high-confidence pseudo-label technique were designed to guide representation learning and clustering allocation. A new loss function has been designed to explore potential data structures and improve clustering performance by introducing contrastive loss. Extensive experiments on multiple benchmark datasets have shown that our method is comparable to state-of-the-art methods.

Nowadays some progress has been made in learning the representation of nodes in unlabeled multi-view for clustering. However, current multi-view graph clustering methods ignore important clustering information during training leading to limited performance. In this paper, we introduce a new framework for multi-view graph clustering, known as IGMC. It utilizes both node attributes and graph topology and uses network topology and the pseudo-labels obtained during the training process as supervisory signals to construct pairs of samples with high discriminative ability and high reliability so that each node corresponds to multiple positive samples. In addition, the clustering quality of the node representations is improved by maximizing the mutual information between the node and the corresponding clusters to emphasize the classes of the nodes. IGMC produces better results than advanced methods on several challenging datasets. The source code is available at https://github.com/tczgithub/IGMC.

Data in modern industrial applications and data science present multidimensional progressively, the dimension and the structural complexity of these data are becoming extremely high, which renders existing data analysis methods and machine learning algorithms inadequate to the extent. In addition, high-dimensional data in actual scenarios often share some common latent components and patterns, it is necessary and significant to analyze such data in an associative manner, rather than treating them independently. Considering the problem of data islands and data privacy that is prevalent in the industry. In this article, we propose the first joint high-order orthogonal iterative (J-HOOI) algorithm for simultaneous tensor decomposition and federated tensor decomposition (FTD) model for feature extraction and dimension reduction of high-dimensional industrial data under the federated learning framework. Moreover, we also develop a secure federated computation process based on the J-HOOI method. Using this method, multiple participants iteratively calculate the local factor matrices and transfer the local information to the parameter server, which aggregates the local information to generate the globally updated factor matrices. Finally, each client generates globally compressed features by projecting local data onto these common potential spaces. We have demonstrated with real-world industrial datasets that our approach is similar to a centralized training model in decomposition accuracy and classification accuracy while respecting privacy.

BACKGROUND: Accumulated evidence shows that the abnormal regulation of long non-coding RNA (lncRNA) is associated with various human diseases. Accurately identifying disease-associated lncRNAs is helpful to study the mechanism of lncRNAs in diseases and explore new therapies of diseases. Many lncRNA-disease association (LDA) prediction models have been implemented by integrating multiple kinds of data resources. However, most of the existing models ignore the interference of noisy and redundancy information among these data resources. RESULTS: To improve the ability of LDA prediction models, we implemented a random forest and feature selection based LDA prediction model (RFLDA in short). First, the RFLDA integrates the experiment-supported miRNA-disease associations (MDAs) and LDAs, the disease semantic similarity (DSS), the lncRNA functional similarity (LFS) and the lncRNA-miRNA interactions (LMI) as input features. Then, the RFLDA chooses the most useful features to train prediction model by feature selection based on the random forest variable importance score that takes into account not only the effect of individual feature on prediction results but also the joint effects of multiple features on prediction results. Finally, a random forest regression model is trained to score potential lncRNA-disease associations. In terms of the area under the receiver operating characteristic curve (AUC) of 0.976 and the area under the precision-recall curve (AUPR) of 0.779 under 5-fold cross-validation, the performance of the RFLDA is better than several state-of-the-art LDA prediction models. Moreover, case studies on three cancers demonstrate that 43 of the 45 lncRNAs predicted by the RFLDA are validated by experimental data, and the other two predicted lncRNAs are supported by other LDA prediction models. CONCLUSIONS: Cross-validation and case studies indicate that the RFLDA has excellent ability to identify potential disease-associated lncRNAs.