With the rise of vertical segmentation in real-world data, federated graph-level clustering has gained significant attention in recent years. However, the inherent missing attributes in graph datasets held by certain clients lead to suboptimal local parameter updates and misaligned global parameter consensus. This results in knowledge shifts during negotiation to ultimately impair overall clustering performance. This issue remains largely underexplored in the current advanced research. To bridge this gap, we propose a novel deep learning network called Federated Graph-level Clustering Network with Attribute Inference (FedAI), which utilizes high-confidence prior knowledge from each domain and multi-party collaborative optimization to achieve efficient reasoning of unknown features. Specifically, on the client, high-confidence graph samples are projected into a latent space. We then extract and upload irreversible path digest information and attribute-oriented inference signals from them. On the server, we first identify affinity relationships hierarchically via the improved graph kernel method. We then infer the features of clients lacking node attributes through a prior structure-guide recovery operator, facilitating inter-client knowledge transfer for better clustering. Experimental results on 15 cross-dataset and cross-domain non-IID graph datasets demonstrate that FedAI consistently outperforms existing methods.

In the federated clustering task, structural heterogeneity across clients inevitably impedes effective multi-source information sharing. To solve this issue, Personalized Federated Learning (PFL) has emerged as a potentially effective solution for image and text clustering. Unlike Euclidean data, graph-structured data exhibits diverse and fragile local patterns, which widely exist in real-world scenarios. Multi-graph data analysis in the federated learning setting is challenging and important, yet remains underexplored. This motivates us to propose a novel PERsonalized Federated graph-lEvel Clustering neTwork (PERFECT), which generates a specialized aggregation strategy for each client by uploading key model parameters and representative samples without sharing private information. Specifically, for each client, we first reconstruct privacy-preserving representative samples in a min-max optimization manner and then upload these samples to the server for subsequent personalized parameter aggregation. On the server, we first extract graph-level embeddings from the uploaded data, and then estimate affinities among multiple learned embeddings to formulate a personalized aggregation strategy for each client. Subsequently, to help each local model better identify the cluster boundaries, we utilize clustering-wise gradient to update the key components in the personalized model parameters from the server. Extensive experimental results have demonstrated the effectiveness and superiority of PERFECT over its competitors.

Node-level federated graph clustering allows multiple unlabeled subgraph holders to collaboratively train on node-level tasks without sharing private information. Existing methods usually assume that the node attributes are complete and have achieved promising progress. However, in the Federated Graph Learning (FGL) scenarios, this assumption is overly strict due to failures in data collection devices. Consequently, most existing FGL frameworks struggle to extract useful features from attribute-incomplete graphs for clustering, yet the issue remains underexplored. To bridge this gap, we propose a causally-aware attribute completion for Incomplete Federated Graph Clustering (IFedGC), which constructs a reliable global causal structure that incorporates clustering-friendly information to guide attribute completion for each subgraph. Specifically, in the attribute completion step, we first construct the causal structure to extract the causal relationships between initialized features, and then upload them to the server. Subsequently, we integrate multiple uploaded causal structures into a global causal one to achieve cross-client attribute completion. Moreover, to support reliable clustering, we first collect the high-confidence cluster centroids from each subgraph using a Graph Neural Network (GNN) model and subsequently aggregate these centroids on the server. The above two steps are seamlessly integrated into a unified FGL framework to obtain a clustering-oriented causal structure, which is sent back to the client to promote high-quality attribute completion for better clustering. Extensive results on five benchmark datasets demonstrate the effectiveness and superiority of IFedGC against its competitors.

Vision Transformer (ViT) has become one of the cornerstones of the computer vision field, demonstrating exceptional performance. However, its inherent high computational complexity and inference latency still pose significant obstacles for deployment in resource-constrained environments. Token pruning, by removing less informative tokens, offers an effective strategy to reduce computational overhead. However, existing pruning methods largely rely on static or local token importance scores. This myopic approach fundamentally overlooks the sequential dependency of pruning decisions and fails to capture the interaction effects between pruning decisions across layers, often neglecting the global interactions between mask variables. To address this limitation, we propose V-Pruner, a fast and globally-informed token pruning framework for Vision Transformer. V-Pruner first leverages Fisher information to perform an initial assessment of token importance, providing a principled initial prior for pruning decisions. Building on this, V-Pruner introduces a Reinforcement Learning (RL) Proximal Policy Optimization (PPO) algorithm, refining token pruning into a global sequential decision process. The algorithm combines a composite reward signal that incorporates both model performance and computational cost to guide policy exploration, effectively evaluating the long-term impact of different pruning decision combinations on global model performance. Extensive experiments on ViT-L, DeiT-B, DeiT-S, and DeiT-T demonstrate that V-Pruner achieves a better balance between accuracy, GFLOPs, inference speed, and training time, surpassing existing mainstream ViT pruning algorithms in overall performance.

Clustering is a fundamental task in graph data mining, including both node-level and graph-level clustering. While the former has been extensively explored to capture local structures and features, the latter has gained attention for its ability to capture global relationships and high-level abstractions. However, existing methods often address these two tasks in isolation, which not only wastes computational resources but also fails to fully leverage the knowledge from both levels to improve each other, hindering consistent performance improvement. To this end, we propose a novel Unified Graph Clustering Network called UGCN, which employs both local and global graph information to address node- and graph-level clustering collaboratively. In detail, we design a dual-branch projector that performs joint learning at both node and graph levels. The first branch extracts node-level features and projects them into distinct cluster layers, where the derived prototypes are used to refine graph attributes and highlight clustering-friendly substructures. In parallel, the second branch captures subgraph embeddings and aggregates them into discriminative graph-level representations. we align the two branches through joint contrastive objectives to establish a bidirectional interaction: refined prototypes guide subgraph and graph-level clustering, while graph-level pseudo-labels provide feedback to enhance node-level clustering. Extensive experimental results across seven datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches.

Federated graph-level clustering (FGC) provides an effective solution for analyzing decentralized graph data with privacy protection. Existing methods typically assume that all clients have the same number of clusters. This assumption simplifies the learning task and has achieved preliminary success. However, this assumption rarely holds in practice, as clients often exhibit substantial heterogeneity in both data distributions and semantic granularity. As a result, cluster-specific knowledge becomes misaligned during server-side aggregation, which ultimately degrades the overall clustering performance. To address this challenge, we propose a novel Federated Graph Clustering under Inter-Client Cluster Number Discrepancy (FedCND) framework, which aligns inter-client heterogeneous distributions by decoupling graph data into public and private patterns. Specifically, after initial local training and clustering on each client, we design a public learner and a private learner to model public and private graph data, respectively. Only anonymized, cluster-level public information is uploaded to the server, while private information remains local. On the server, cluster-level public prototypes are aggregated based on affinities between reconstructed cluster-level graphs, enabling privacy-preserving prototype alignment across clients with heterogeneous cluster numbers and mitigating interference from misaligned information during global aggregation. Finally, private subgraphs derive client-specific prototypes through local relearning, which are subsequently fused with globally oriented public prototypes for better clustering. Extensive experiments demonstrate that the proposed FedCND achieves an average of 4.9% accuracy improvement against current state-of-the-art methods.

Federated graph learning (FGL), which excels in analyzing non-IID graphs as well as protecting data privacy, has recently emerged as a hot topic. Existing FGL methods usually train the client model using labeled data and then collaboratively learn a global model without sharing their local graph data. However, in real-world scenarios, the lack of data annotations impedes the negotiation of multi-source information at the server, leading to sub-optimal feedback to the clients. To address this issue, we propose a novel unsupervised learning framework called Federated Graph-level Clustering Network (FedGCN), which collects the topology-oriented features of non-IID graphs from clients to generate global consensus representations through multi-source clustering structure sharing. Specifically, in the client, we first preserve the prototype features of each cluster from the structure-oriented embedding through clustering and then upload the learned multiple prototypes that are hard to be reconstructed into the raw graph data. In the server, we generate consensus prototypes from multiple condensed structure-oriented signals through Gaussian estimation, which are subsequently transferred to each client to promote the great encoding capacity of the local model for better clustering. Extensive experiments across multiple non-IID graph datasets have demonstrated the effectiveness and superiority of FedGCN against its competitors.

Medical image segmentation models have play a significant and essential role in modern healthcare, while excessive computational and storage resources limit their deployment in real-world medical scenarios. To address these challenges, structured pruning has emerged as a promising solution for compressing medical image segmentation models, allowing for the removal of entire components while preserving their regular structure. Nevertheless, existing structured pruning methods often fail to fully exploit the unique architectural characteristics of segmentation models, such as the encoder-decoder symmetry in CNNs or the residual connections in Transformers. In addition, these methods often neglect the impact of pruning on the model's activation statistics, leading to potential performance degradation. In this paper, we propose a novel structured pruning method that specifically targets these limitations by introducing Feature Group Clustering (FGC) and Spectral Variance Rebalancing (SVR) to effectively reduce redundancy of models while maintaining their statistical properties. Specifically, FGC unifies the handling of CNN-based and Transformer-based architectures by treating their components as feature groups, and employing Spectral Clustering to eliminate redundancy while preserving critical structures. Furthermore, SVR restores the statistical properties of the pruned model by analytically rescaling normalization parameters based on intra-cluster spectral cor-relations. Extensive experiments on multiple models including 3D TransUNet, Swin UNETR, and MedFormer across Synapse Multi-organ CT, BraTS2020, Abdomen CT and Abdomen MRI demonstrate that our method outperforms existing techniques in both segmentation performance and compression effects.

The Internet of Medical Things (IoMT) has emerged as a research hotspot in both academic circles and medical institutions. Within IoMT systems, IoT devices collect and upload patient data via sensors, enabling doctors to provide remote treatment to patients. However, the sensitive data involved in IoMT has raised concerns regarding user authentication and data privacy. To address these issues, signcryption has emerged as a promising solution, offering integrity, confidentiality, and unforgeability. Unfortunately, most existing signcryption schemes are not practical for IoMT due to their high computational and storage requirements. In this paper, we propose a signcryption scheme that can provide efficient identity authentication and data sharing for IoMT. Our designed scheme facilitates the secure transmission of medical data between doctors and patients, effectively verifies user legitimacy, and minimizes the risk of private information leakage. To achieve this, we leverage aggregate signature technology to batch verify the correctness of patients' medical data. We also formally prove the security of our proposed design, including existential unforgeability against chosen message attack (EU-CMA) and indistinguishability against chosen plaintext attack (IND-CPA). Finally, comprehensive performance evaluations show that compared with existing schemes, our verification time remains stable at 0.05 seconds, independent of the number of messages. The evaluation results demonstrate that our solution is practical and efficient.

The rapid development of Convolutional Neural Networks (CNNs) and Transformer-based architectures has significantly enhanced medical image segmentation. However, the increasing computational and storage overhead poses substantial challenges for their deployment in real-world resources-limited medical scenarios. Furthermore, the heterogeneity in diverse architectures has made it difficult to develop a unified compression technique that can effectively and efficiently prune these models. To address these challenges, we propose a novel Topology-Consistent pruning method with Fisher Information (TCFI), which uniformly compresses medical image segmentation networks regardless of their architectural differences. Our method employs graph representations to identify topology-consistent substructures, which are parameter groups that share similar computational patterns and should be pruned together. In addition, we leverage Fisher Information as a principled statistical measure to evaluate the parameters’ significance during pruning. Extensive experiments on 2D and 3D datasets of CNN-based and Transformer-based medical image segmentation networks demonstrate the superior performance of our pruning method.

Subgraphs of a complete graph are usually distributed across multiple devices and can only be accessed locally because the raw data cannot be directly shared. However, existing node-level federated graph learning suffers from at least one of the following issues: 1) heavily relying on labeled graph samples that are difficult to obtain in real-world applications, and 2) partitioning a complete graph into several subgraphs inevitably causes missing links, leading to sub-optimal sample representations. To solve these issues, we propose a novel $\underline{\text{Fed}}$erated $\underline{\text{N}}$ode-level $\underline{\text{C}}$lustering $\underline{\text{N}}$etwork (FedNCN), which mends the destroyed cross-subgraph links using clustering prior knowledge. Specifically, within each client, we first design an MLP-based projector to implicitly preserve key clustering properties of a subgraph in a denoising learning-like manner, and then upload the resultant clustering signals that are hard to reconstruct for subsequent cross-subgraph links restoration. In the server, we maximize the potential affinity between subgraphs stemming from clustering signals by graph similarity estimation and minimize redundant links via the N-Cut criterion. Moreover, we employ a GNN-based generator to learn consensus prototypes from this mended graph, enabling the MLP-GNN joint-optimized learner to enhance data privacy during data transmission and further promote the local model for better clustering. Extensive experiments demonstrate the superiority of FedNCN.

Variational autoencoders (VAEs) have been deployed in many privacy-sensitive domains, and their vulnerability to membership inference attacks (MIAs) poses giant privacy risks. While some existing privacy protection methods like differential privacy often compromise generative models’ utility, we present GuidedLatent, a novel mechanism that enhances membership privacy and preserves their generative performance. GuidedLatent allows the model to adjust latent representations dynamically based on distribution similarities, coupled with a two-phase training strategy that gradually incorporates privacy constraints. We also establish bounds on the privacy-utility trade-off theoretically and prove our mechanism reduces the performance of membership inference attacks compared to other baseline approaches. Extensive experiments demonstrate that our method maintains high-quality generation capabilities while minimizing degradation in quality metrics. Our method performs effectively across various VAE variants and architectures, providing a practical solution for privacy-preserving generative models.1

Federated Learning (FL) has become an effective method for improving medical image segmentation performance under privacy protection. However, the heterogeneity between medical image modalities, including background differences, variations in detail presentation, and resolution discrepancies, presents challenges for enhancing the accuracy of multi-modal joint segmentation. These differences between modalities may hinder the effective fusion of information from each modality, thus affecting the accuracy and consistency of segmentation results. To address this issue, this study proposes a novel federated medical image segmentation method, DCT-GMM-FedSeg. This method combines Discrete Cosine Transform (DCT) and Gaussian Mixture Model (GMM) to improve segmentation accuracy while preserving privacy. Specifically, DCT is used to extract background frequency information, which is globally unified and integrated with the original background to alleviate modality-related background differences. GMM is used to model image detail features, and by sharing the distribution information of these detailed regions, it reduces the differences between modalities. In this way, federated learning can extract complementary information from different modalities, enhancing global generalization ability and fully leveraging the advantages of multi-modal segmentation. Throughout the process, key image information is retained locally to prevent privacy leakage. Experimental results demonstrate that DCT-GMM-FedSeg significantly improves performance in four heterogeneous medical image segmentation tasks, particularly exhibiting excellent robustness and generalization ability in Non-IID data environments.

Graph-level clustering remains a pivotal yet formidable challenge in graph learning. Recently, the integration of deep learning with representation learning has demonstrated notable advancements, yielding performance enhancements to a certain degree. However, existing methods suffer from at least one of the following issues: 1) the original graph structure has noise, and 2) during feature propagation and pooling processes, noise is gradually aggregated into the graph-level embeddings through information propagation. Consequently, these two limitations mask clustering-friendly information, leading to suboptimal graph-level clustering performance. To this end, we propose a novel Dual Boost-Driven Graph-Level Clustering Network (DBGCN) to alternately promote graph-level clustering and filtering out interference information in a unified framework. Specifically, in the pooling step, we evaluate the contribution of features at the global and optimize them using a learnable transformation matrix to obtain high-quality graph-level representation, such that the model’s reasoning capability can be improved. Moreover, to enable reliable graph-level clustering, we first identify and suppress information detrimental to clustering by evaluating similarities between graph-level representations, providing more accurate guidance for multi-view fusion. Extensive experiments demonstrated that DBGCN outperforms the state-of-the-art graph-level clustering methods on six benchmark datasets.

Graph-level clustering is a fundamental task of data mining, aiming at dividing unlabeled graphs into distinct groups. However, existing deep methods that are limited by pooling have difficulty extracting diverse and complex graph structure features, while traditional graph kernel methods rely on exhaustive substructure search, unable to adaptively handle multi-relational data. This limitation hampers producing robust and representative graph-level embeddings. To address this issue, we propose a novel Multi-Relation Graph-Kernel Strengthen Network for Graph-Level Clustering (MGSN), which integrates Multi-Relation Modeling (MRM) with graph kernel to fully employ their respective advantages. Specifically, MGSN constructs multi-relation graphs to capture diverse semantic relationships between nodes and graphs, which employ graph kernel methods to extract graph affinity, enriching the representation space. Moreover, a Relation-aware Embedding Strengthening Strategy (RESS) is designed, which adaptively aligns multi-relation information across views while strengthening graph-level features through a progressive fusion process. Extensive experiments on multiple benchmark datasets demonstrate the superiority of MGSN over state-of-the-art methods. The results highlight its ability to leverage multi-relation structures and graph kernel features, establishing a new paradigm for robust graph-level clustering.

As a fine-grained sentiment analysis task, Aspect-Level Multimodal Sentiment Analysis (AMSA) aims to identify the sentiment polarity of each aspect term within given text-image pairs. Existing methods simply utilize attention mechanisms to adaptively search for the associated sentiment between aspects in a sentence, overlooking the fact that sentiment judgments can be easily interfered with by other irrelevant words. Additionally, blindly leveraging image information may result in coarse details, which fail to accurately capture aspect-specific information or overlook global sentiment trends. To address these challenges, we propose a novel Aspect-Oriented Semantic Enhancement Network (ASEN) for aspect-level multimodal sentiment analysis. Specifically, our model contains an aspect-aware enhancement module that is sensitive to aspect-related semantic information based on syntactic structure and part-of-speech information. Furthermore, we introduce an aspect-oriented image sentiment module that precisely captures sentiment-relevant visual cues corresponding to different aspect terms through an adjective mapping method. To capture the overall sentiment trend, we employ a global sentiment perception module that provides auxiliary sentiment information to enhance aspect-based sentiment analysis. Experiment results show that our method achieves state-of-the-art results on the Twitter-2015 and Twitter-2017 datasets.

Face age editing typically utilizes GAN or StyleGAN as the underlying framework, employing CNN or Transformer to engineer sophisticated modules for the subsequent processing of facial latent codes. Notwithstanding the laudable endeavors of researchers in this domain, these methods still face challenges, including facial attribute entanglement and suboptimal age modification. For instance, the process of editing may result in the reversal of gender, the presence of discernible artifacts, and the inability to achieve the intended effect regarding age. To address the aforementioned limitations, inspired by the newly proposed Extended Long Short-Term Memory (xLSTM), we explore the application of xLSTM in the facial age editing task for the first time. With the well-designed Style-mLSTM module, we achieve accurate retention of facial attributes while seamlessly transitioning between successive age modifications. In addition, considering the negative impact of the imbalanced age distribution in the existing dataset on the editing effect of different age groups, we propose a Weighted Age Distribution Calibration (WADC) mechanism to effectively mitigate this problem. Qualitative and quantitative experiments demonstrate that our approach outperforms existing techniques on several evaluation metrics and effectively demonstrates the great potential of xLSTM in facial attribute editing tasks.

Long-term Time Series Forecasting (LTSF) is an important task with extensive applications across diverse domains. While contemporary methodologies have achieved notable results through the integration of time and frequency domain features, significant challenges persist. Current approaches frequently disregard the information degradation inherent in Fast fourier transform (FFT) and inverse Fast fourier transform (IFFT) operations, substantially compromising predictive accuracy. Furthermore, conventional weighting mechanisms demonstrate limitations in their capacity to capture the intricate relationships between temporal and frequency representations, leading to suboptimal feature fusion and consequent information loss. To address these limitations, we present the Joint Time-Frequency Method (JTFM), a novel framework that simultaneously extracts sequence features from both temporal and frequency domains, thereby transcending single-domain constraints and enhancing feature comprehensiveness. Additionally, we introduce the Dynamic Harmonic Accumulation Weighting Mechanism (DHAWM), which surpasses traditional weighting approaches by dynamically modulating the relative contributions of temporal and frequency domain features based on sequence-specific characteristics. This adaptive mechanism strengthens the model’s feature representation capabilities and enhances forecasting precision. Empirical validation on eight real-world datasets demonstrates the JTFM’s superior performance compared to state-of-the-art baseline methods, establishing its efficacy in long-term time series forecasting applications.

Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tests, which lack spatial resolution and the ability to detect localized changes. However, CT-based prediction faces two major challenges: the high computational complexity of transformer-based architectures, which limits their deployment in portable and clinical settings, and the imbalanced, long-tailed distribution of real-world hospital data that skews predictions. To address these issues, we introduce MedConv, a convolutional model for bone density prediction that outperforms transformer models with lower computational demands. We also adapt Bal-CE loss and post-hoc logit adjustment to improve class balance. Extensive experiments on our AustinSpine dataset shows that our approach achieves up to 21% improvement in accuracy and 20% in ROC AUC over previous state-of-the-art methods. Code will be available at https://github.com/Richardqiyi/MedConv.

In recent years, Vision Transformers (ViT) have achieved significant success in various complex visual tasks, but they also come with substantial computational costs and memory overheads. To address this issue, lightweight Vision Transformers have become an important research direction. Current research on lightweight ViTs mainly focuses on combining CNNs and Transformers, leveraging the advantages of CNNs in local feature extraction while utilizing Transformers’ ability to model global context. However, existing lightweight models often suffer from an imbalance in processing low-frequency global information and high-frequency local information. While sparse attention mechanisms effectively capture global context and reduce computational load, they typically adopt relatively simple strategies for handling high-frequency local information, failing to fully exploit the details of local features. To address this issue, we introduce a new lightweight Vision Transformer model, A Lightweight Vision Transformer for Balancing Global and Local Information (GLFormer). GLFormer combines dynamic weight adjustment with context-aware mechanisms to effectively aggregate high-frequency local information, optimizing the balance between global and local information. Additionally, we introduce a Depth Perception Feed-Forward Network (DPFFN), which further enhances feature fusion and detail refinement, thus enhancing the model’s performance and its capacity to generalize. Based on GLFormer and DPFFN, we design a novel visual backbone network—GLNet. Extensive experimental results show that GLNet consistently demonstrates excellent performance across various tasks, while maintaining a relatively low computational cost.

Event causality identification (ECI) is crucial for understanding causal relationships in text. Despite the progress in large language models (LLMs), these models still struggle with causal reasoning due to biases in pre-training data and difficulties in correctly interpreting causal semantics. This often leads to inconsistent predictions, where models infer causal relationships not explicitly supported by the text. To address these challenges, we propose a novel debiasing framework that integrates causal intervention via back-door adjustment, significantly enhancing LLMs’ causal reasoning capabilities. Our approach integrates back-door adjustment through a structural causal model (SCM), where external knowledge from ConceptNet serves as a back-door variable to disentangle confounding biases. We further introduce causal cues to guide LLMs’ attention toward valid causal semantics and causal strength estimation to refine effect quantification. Experimental results on two widely adopted ECI benchmark datasets demonstrate the superior effectiveness of our approach compared to state-of-the-art LLM-based methods, including GPT-4.

Large language models (LLMs) have achieved significant success in complex tasks across various domains, but these achievements come with high computational costs and long inference delays. Pruning, as an effective optimization technique, simplifies model structures by removing redundant components, thereby improving model generalization and operational efficiency. Although existing pruning retraining-free algorithms perform excellently in pruning time, these algorithms often focus on local optimal solutions in encoder-based language models, lacking comprehensive exploration of global optimal solutions, which may affect the overall model performance. To address this issue, we propose a novel retraining-free structured pruning algorithm, named RL-Pruner. The algorithm consists of two main stages: the Mask Rearrangement Based on Asynchronous Advantage Actor-Critic (MA3C) stage and the BiConjugate Gradient Solver for Mask Tuning (BGMT) stage. It aims to explore the intra-layer interactions of mask variables and efficiently find the global optimal solution without requiring retraining. We evaluate this method using BERTBASEand DistilBERT models on the GLUE and SQuAD benchmark tests. Experimental results show that RL-Pruner significantly improves accuracy on the SQuAD1.1benchmark. Under a 60% FLOPs constraint, compared with existing pruning retraining-free algorithms, the F1 score increases by 4.25%.

Time series anomaly detection holds notable importance for risk identification and fault detection across diverse application domains. Unsupervised learning methods have become popular because they have no requirement for labels. However, due to the challenges posed by the multiplicity of abnormal patterns, the sparsity of anomalies, and the growth of data scale and complexity, these methods often fail to capture robust and representative dependencies within the time series for identifying anomalies. To enhance the ability of models to capture normal patterns of time series and avoid the retrogression of modeling ability triggered by the dependencies on high-quality prior knowledge, we propose a differencing-based contrastive representation learning framework for time series anomaly detection (DConAD). Specifically, DConAD generates differential data to provide additional information about time series and utilizes transformer-based architecture to capture spatiotemporal dependencies, which enhances the robustness of unbiased representation learning ability. Furthermore, DConAD implements a novel KL divergence-based contrastive learning paradigm that only uses positive samples to avoid deviation from reconstruction and deploys the stop-gradient strategy to compel convergence. Extensive experiments on five public datasets show the superiority and effectiveness of DConAD compared with nine baselines. The code is available at https://github.com/shaieesss/DConAD.

Fraudulent activities have significantly increased across various domains, such as e-commerce, online review platforms, and social networks, making fraud detection a critical task. Spatial Graph Neural Networks (GNNs) have been successfully applied to fraud detection tasks due to their strong inductive learning capabilities. However, existing spatial GNN-based methods often enhance the graph structure by excluding heterophilic neighbors during message passing to align with the homophilic bias of GNNs. Unfortunately, this approach can disrupt the original graph topology and increase uncertainty in predictions. To address these limitations, this paper proposes a novel framework, Dual-channel Heterophilic Message Passing (DHMP), for fraud detection. DHMP leverages a heterophily separation module to divide the graph into homophilic and heterophilic subgraphs, mitigating the low-pass inductive bias of traditional GNNs. It then applies shared weights to capture signals at different frequencies independently and incorporates a customized sampling strategy for training. This allows nodes to adaptively balance the contributions of various signals based on their labels. Extensive experiments on three real-world datasets demonstrate that DHMP outperforms existing methods, highlighting the importance of separating signals with different frequencies for improved fraud detection. The code is available at https://github.com/shaieesss/DHMP.

Remote sensing change detection tracks surface transformations over time, aiding in disaster early warning and urban change monitoring. However, current methods struggle with challenges such as complex semantic interpretation, sensor variations, seasonal changes, and suboptimal model designs, which hinder accurate detection. To overcome these issues, we propose a method combining semantic enhancement and efficient temporal cross-perception. First, we enhance relational semantics by visualizing features at various levels. Shallow features are enhanced using a reversible method, while deep features are strengthened through a graph-structured non-Euclidean approach to capture global relationships. Second, we introduce an efficient bi-temporal interaction method that uses spatial matrix compression and matrix multiplication (similar to "QKV") for cross-temporal understanding, focusing on temporal changes. Finally, to address insufficient weight learning in distant decoder layers, we apply weight normalization transfer from better-understood layers, improving understanding in the generator. Our method outperforms baseline approaches, with 3.44% IoU improvement on CLCD and 1.23% IoU improvement on Google.

Remote sensing change detection identifies and locates surface changes from multi-temporal remote sensing images, supporting applications such as environmental monitoring, disaster assessment, and land use management. Current deep learning methods for high-resolution remote sensing change detection face challenges, including high computational costs for bi-temporal interactions and inadequate utilization of feature semantics. To address these challenges, we propose a novel method that deeply considers the physical significance of bi-temporal remote sensing images for accurate change detection. Specifically, we introduce a bi-temporal cross-perception approach based on graph compression. By leveraging spatial compaction in graph structures, this method employs cross-attention-based bi-temporal interactions to enhance cross-perception and reduce pseudo-changes caused by isolated semantic understanding. Additionally, we efficiently integrate features from hierarchical CNNs by separately considering low- and high-level features. For low-level features, we apply a contrastive learning-based semantic enhancement strategy to clearly differentiate change regions from background. For high-level features, we propose an adaptive bi-temporal feature fusion method to avoid the generalization issues of fixed learnable parameters. Experimental results on the CLCD and Google datasets demonstrate that our method outperforms baseline methods in both IoU and F1 scores.

Natural Language Processing (NLP) has achieved significant success in complex tasks across various domains, yet it also brings high computational costs and inference delays. Pruning, as a model optimization technique, can effectively reduce model complexity and enhance its generalization capability and efficiency. However, current encoder-based language model pruning algorithms often lack robust dynamic adaptability and tend to focus only on short-term optimal solutions, without fully considering the interactions between different solutions. This limits their ability to find global optima, thereby potentially impacting overall model performance. To address these challenges, we propose a structured pruning algorithm based on reinforcement learning, named RLM (Reinforcement Learning Masking), which includes QLOM (Q-Learning Optimization Mask) and QRMT (Quasi-Minimal Residual Mask Tuning) components. This algorithm aims to rapidly and effectively find global optima without the need for retraining. We evaluated this method using BERTBASEand DistilBERT models on the GLUE and SQuAD benchmarks. Experimental results show that RLM significantly enhances model accuracy in the SQuAD benchmark. Under a 60% FLOPs constraint, RLM achieves a 8.45% increase in F1 score compared to existing retraining-free pruning algorithms, demonstrating its effectiveness in improving performance while managing computational resources efficiently.

Deep graph clustering, as a fundamental task in data mining, has attracted widespread attention. Recently, excellent performance has been achieved by integrating graph structure and node attributes to generate consensus latent embeddings. However, existing clustering methods are limited by redundant information and unreliable clustering distribution, which hinders the discriminative power of the latent embeddings. To address this issue, we propose a novel deep graph clustering framework called Multi-dimensional Topological Association Strengthening Clustering Network (MTASCN). Specifically, we design a Multi-dimensional Feature Association Mechanism (MFAM), which extracts the competitive or cooperative relationship between features to alleviate the interference of redundant features and enhance the dominant features. In addition, we develop a Structure-oriented Multi-order Loss Module (SMLM) that reinforces the generation of clustering distribution under reliable structure information guidance by calculating the multi-order similarity between the latent embeddings and the original graph structure. Extensive experiments on five benchmark datasets have demonstrated that MTASCN consistently outperforms other clustering methods.