Federated learning (FL) has emerged as a promising solution to enable distributed learning without sharing sensitive data. However, FL is vulnerable to data poisoning attacks, where malicious clients inject malicious data during training to compromise the global model. Existing FL defenses suffer from the assumptions of independent and identically distributed (IID) model updates, asymptotic optimal error rate bounds, and strong convexity in the optimization problem. Hence, we propose a novel framework called Federated Learning Optimal Transport (FLOT) that leverages the Wasserstein barycentric technique to obtain a global model from a set of locally trained non-IID models on client devices. In addition, we introduce a loss function-based rejection (LFR) mechanism to suppress malicious updates and a dynamic weighting scheme to optimize the Wasserstein barycentric aggregation function. We provide the theoretical proof of the Byzantine resilience and convergence of FLOT to highlight its efficacy. We evaluate FLOT on four benchmark datasets: GTSRB, KBTS, CIFAR10, and EMNIST. The experimental results underscore the practical significance of FLOT as an effective defense mechanism against data poisoning attacks in FL while maintaining high accuracy and scalability. Also, we observe that FLOT serves as a robust client selection technique under no attack, which demonstrates its effectiveness.

The proliferation of big data has fueled the success of deep learning; however, its inherent ”black box” nature poses significant challenges for its adoption in safety-critical domains. Existing interpretable machine learning methods offer partial solutions but often struggle with model fidelity, inconsistent explanations, a lack of holistic model understanding, and critically, computational inefficiency, especially when applied to models trained on large-scale datasets. To overcome these hurdles, this paper introduces Parallel Explainer (PEXP), an innovative parallel tree-based interpretation framework designed for scalability and comprehensive understanding. PEXP initiates by generating a localized sample set around a target instance through data distribution-aware perturbations. It then computes similarity scores and employs a kernel function to weight these samples effectively. Leveraging concepts from Bagging and Boosting, PEXP efficiently constructs Parallel Ensemble Trees as its core interpretable model. This model provides feature importance-based explanations and aggregates insights across all samples to achieve a global understanding of the model's behavior on the entire dataset. Experimental results demonstrate PEXP's significant advantages over mainstream interpretable methods in both runtime efficiency and the quality of explanations, particularly crucial for big data analytics. Furthermore, a case study illustrates PEXP's application in enhancing the interpretability of video anomaly detection systems within smart cities, a domain characterized by large volumes of data and offers insights for improving Transformer-based architectures.

The utilization of graph neural networks in heterogeneous networks has been rapidly increasing in recent years. The topological structure, fundamental to the nature of graphs, is often claimed to be jointly addressed with attribute information by most heterogeneous graph neural network (HGNN) approaches. However, this assertion lacks sufficient empirical validation. We empirically challenge these claims within existing evaluation frameworks. We propose a straightforward multi-layer perceptron (MLP) based model which relies solely on adjacency relationships for feature aggregation, without fully exploiting the graph's intricate topological structures. Unexpectedly, the model achieved nearly state-of-the-art performance on several real-world datasets. This discrepancy indicates that current evaluation protocols contain systemic biases and often fail to distinguish superficial adjacency exploitation from genuine structural pattern learning. It also points to the need for future benchmark datasets and metrics that more faithfully reflect the real requirements of topological learning. We hope this work stimulates further research into the role and significance of topological information in HGNNs.

Multi-label learning plays a crucial role in numerous real-world applications, where each instance may be associated with multiple semantic labels. However, in practical scenarios, label noise is widespread and poses a significant challenge, as it can simultaneously distort multiple labels due to ambiguous annotations, human fatigue, or automated labeling inaccuracies. While considerable progress has been made in developing noise-robust methods for single-label learning, addressing noise in multi-label settings remains substantially more challenging due to the intricate interplay among multiple potentially corrupted labels. This underscores the pressing need for effective label correction strategies tailored to noisy multi-label learning. To address this gap, we propose a latent contrastive embedding framework designed for noisy multi-label scenarios. The approach not only learns robust feature representations through supervised contrastive learning but also dynamically identifies clean labels via a small-loss guided sample selection strategy. Moreover, the embedding and label correction processes are jointly optimized, allowing the model to capture the semantic structure of both features and labels under noisy conditions. Specifically, we adopt a small-loss criterion to distinguish clean from noisy samples during the early training phase. In addition, a balanced loss is introduced to mitigate the effects of label imbalance and sample difficulty. Finally, comprehensive experiments conducted under various patterns and levels of label noise demonstrate the superior robustness and generalization ability of the proposed method in noisy multi-label classification tasks.

Cross-domain recommendation can combine users' interests in multiple domains to achieve diversification of recommended content. To solve the problem of complex and changeable interest relationship among different domains, this paper proposes a cross-domain recommendation model integrating user's long-term and short-term interests. Firstly, to solve the problem of different data distributions in different domains, this paper proposes the graph convolutional network with maximum mean discrepancy (MMD), which gradually aligns the feature representation of shared potential space during training to reduce the influence of negative transfer. Secondly, to solve the problem of different features of items in different domains, considering the advantage of attention mechanism in distinguishing importance, a hierarchical attention mechanism focusing on item features is proposed to build users' short-term interests in source domain. Finally, aiming at the dynamic influence of users' long-term and short-term interest, a multi-type interest dynamic aggregation module based on gated network is proposed, which not only integrates users' preferences in different domains, but also takes into account the characteristics of items to be predicted. Experiments show that the model can effectively capture users' multi-type interests in source domain and target domain on real data set, so as to improve the recommendation accuracy of target domain.

Graph-based multi-view spectral clustering methods have achieved notable progress recently, yet they often fall short in either oversimplifying pairwise relationships or struggling with inefficient spectral decompositions in high-dimensional Euclidean spaces. In this paper, we introduce a novel approach that begins to generate hypergraphs by leveraging sparse representation learning from data points. Based on the generated hypergraph, we propose an optimization function with orthogonality constraints for multi-view hypergraph spectral clustering, which incorporates spectral clustering for each view and ensures consistency across different views. In Euclidean space, solving the orthogonality-constrained optimization problem may yield local maxima and approximation errors. Innovately, we transform this problem into an unconstrained form on the Grassmannian manifold. Finally, we devise an alternating iterative Riemannian optimization algorithm to solve the problem. To validate the effectiveness of the proposed algorithm, we test it on four real-world multi-view datasets and compare its performance with six state-of-the-art multi-view clustering algorithms. The experimental results demonstrate that our method outperforms the baselines in terms of clustering performance due to its superior low-dimensional and resilient feature representation.

Public vulnerability databases, such as the National Vulnerability Database (NVD), document vulnerabilities and facilitate threat information sharing. However, they often suffer from short descriptions and outdated or insufficient information. In this paper, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Zad</i>, a system designed to enrich NVD vulnerability descriptions by leveraging external resources. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Zad</i> consists of two pipelines: one collects and filters supplementary data using two encoders to build a detailed dataset, while the other fine-tunes a pre-trained model on this dataset to generate enriched descriptions. By addressing brevity and improving content quality, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Zad</i> produces more comprehensive and cohesive vulnerability descriptions. We evaluate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Zad</i> using standard summarization metrics and human assessments, demonstrating its effectiveness in enhancing vulnerability information.

In recent years, the semantic segmentation of multimodal remote-sensing images using convolutional methods has received significant attention. Owing to the localized nature of convolutional operations, existing methods use the attention method to obtain global relations. However, effectively complementing and eliminating the global and local relations between two modalities has become a major challenge. In addition, category imbalance often affects the model performance as a result of the high resolution of remote-sensing images. In this study, we propose an asymmetric dual encoder network with clustering mutual contrast loss. Specifically, we use a convolutional neural network and Transformer as the backbone to extract two modal features in parallel to learn the local and global information, respectively. Next, our proposed multimodal hierarchical interaction module and dynamic weight inspired block efficiently fuse the multimodal features to complement the local and global information. The fused features are fed into our proposed local context extraction module and global context extraction module. Furthermore, to address the challenge presented by feature class imbalances, we apply a clustering algorithm to classify each pixel, which is subsequently inter-supervised using the inter-contrast loss. Extensive experiments on benchmark datasets show that the proposed model is extremely effective in the semantic segmentation of remotely sensed images and that it outperforms current state-of-the-art networks both quantitatively and qualitatively. Our code and results can be found at https://github.com/LYZ00918/AMCNet.

LiDAR is one of the most important sensors in the field of autonomous driving and allows for better and more accurate perception of the changes in the surrounding environment. Most of the existing 3D object detection methods use data augmentation and feature fusion enhancement to improve the performance of detection, but the majority of the methods ignore the handling of sample imbalance problems during data augmentation. Also, the designed feature fusion and enhancement methods were not well suited to work with the enhancement methods. To this end, we developed a combined method involving data augmentation and feature enhancement. The designed approach has two main objectives: 1) to address the problem of unbalanced sample distribution in detection scenes through data augmentation, and 2) to enhance feature perception using a special feature enhancement module. Our proposed method solves the problem of class imbalance by directly increasing the number of pedestrian samples in the scene through mixed data augmentation, i.e., RG-Aug. In addition, we introduce the Decoupling and Attention Fusion module (DAF), which combines classification headers with high-level features and prediction branches with low-level features. Leverage data features between different layers of features to get a more robust feature representation. Finally, the multi-scale pyramid attention enhancement module is designed to achieve feature enhancement of multi-scale features by means of attention to improve the detection ability of small objects in the scene, especially the detection ability of pedestrians. Our method can achieve 1.57%, 2.16%, and 2.05% performance improvement on the KITTI dataset for Easy, Mod, and Hard samples, respectively. Furthermore, for the detection of pedestrians, our method has a significant competitive advantage over other state-of-the-art techniques with a mAP of 73.42%.