The Transformer model, with its ability to capture long-term dependencies, has demonstrated significant potential in enhancing long-term traffic flow prediction for effective urban transportation management. However, most existing Transformer-based methods adhere to a centralized approach, failing to address privacy concerns and to optimize computational resource utilization. Although emerging federated learning paradigms offer privacy protection, the average aggregation still overlooks client heterogeneity and lacks the synchronous efficiency required for traffic flow prediction tasks. Consequently, we introduce FedTFormer, a hierarchical federated learning framework tailored to boost the performance of Transformer models in decentralized environments, involving clients, edge servers, and a central server. Initially, clients are organized into clusters through a sophisticated static clustering mechanism anchored in bipartite graph theory. FedTFormer enhances robustness of Transformer by facilitating synchronous average aggregation within clusters. Additionally, it performs asynchronous fine-tuning of cluster-specific parameters, leveraging hypernetwork constructed on the central server. Clients utilize an optimized Transformer model for localized training, harnessing its proficiency in capturing long-term spatio-temporal dependencies. Ultimately, we conduct extensive experiments across three datasets, comparing our method against ten sophisticated approaches and demonstrating the effectiveness and robustness of FedTFormer.

Extreme Gradient Boosting (XGBoost) demonstrates excellent performance in practice and is widely used in both industry and academic research. This extensive application has led to a growing interest in employing multi-party data to develop more robust XGBoost models. In response to increasing concerns about privacy leakage, secure vertical federated XGBoost is proposed. It employs secure multi-party computation techniques, such as secret sharing (SS), to allow multiple parties holding vertically partitioned data, i.e., disjoint features on the same samples, to collaborate in constructing an XGBoost model. However, the running efficiency is the primary obstacle to the practical application of existing protocols, especially in multi-party settings. The reason is that these protocols not only require the execution of data-oblivious computations to protect intermediate results, leading to high computational complexity, but also involve a large number of SS-based non-linear operations with high overheads, e.g., division operations in gain score calculation and comparison operations in best split selection. To this end, we present a secure and efficient multi-party protocol for vertical federated XGBoost, called SecureXGB, which can perform the collaborative training of an XGBoost model in an SS-friendly manner. In SecureXGB, we first propose a parallelizable multi-party permutation method, which can secretly and efficiently permute all samples before model training to reduce the reliance on data-oblivious computations. Then, we design a linear gain score that can be evaluated without involving division operations and has equivalent utility to the original gain score. Finally, we develop a synchronous best split selection method to secretly identify the best split with the maximum gain score using a minimal number of comparison operations. Experimental results demonstrate that SecureXGB can achieve better training efficiency than state-of-the-art protocols without the loss of model accuracy.

Multimodal brain graph transformers have become one of the foundational architectures of graph foundation models for brain science, relying on multimodal brain network fusion. However, most current multimodal brain network fusion methods primarily focus on modality-specific information fusion. The interplays within structural-functional brain networks are often ignored. Therefore, they fail to acquire essential coupling information, which is crucial for obtaining robust joint brain network representations. This oversight inevitably limits the effectiveness and generalization of these representations in various downstream tasks. To this end, we propose a novel joint structural-functional brain graph transformer model (namely sfBGT). Technically, we design a cross-network assortativity quantification mechanism to enable structural-functional brain network coupling, thus capturing the interplays of brain structure and function. We then employ a multimodal graph transformer to effectively learn joint representations of structural-functional brain networks along with their coupling relation representations. Experimental results on three real-world datasets demonstrate the superiority of sfBGT over state-of-the-art baselines.

In recent years, with the rise of intelligent hardware technology, the Internet of Things (IoT) has achieved rapid development and has been widely used in smart cities, smart power grids, industrial Internet, and other fields. The resulting security risks of IoT have attracted more and more attention. Being different from the traditional authentication that is based on MAC or security certificate, RF fingerprinting technology extracts fingerprints from the emissions of wireless transmitters. These fingerprints root in the hardware imperfection of the transmitting circuits and can be used for wireless device identification and authentication. RF fingerprinting can effectively enhance the security of the wireless network and has become a research focus in the field of IoT. However, how to learn and fuse multiple RF fingerprints is still an urgent problem to be solved. Inspired by the attention mechanism in the field of computer vision, an adaptive RF fingerprints fusion network (ARFNet) is proposed in this article, which is built on our dual attention convolution (DAConv) layer. This neural network can extract and adaptively fuse multiple RF fingerprints in a data-driven manner to obtain more discriminant features. In addition, a data augmentation method is also designed to effectively enhance the network’s robustness to channel variation and SNR variation. Extensive experimental results show that the proposed ARFNet combined with data augmentation can achieve 99.5% recognition accuracy on five USRP X310, and achieve 95.7% recognition accuracy on 56 ADS-B devices. Our source code has been released athttps://github.com/zhangweifeng1218/Adaptive_RF_Fingerprinting.

Industrial advancement has introduced a significant impact on ecological balance and natural resources; thus, pollution monitoring using smart sensors in the industrial Internet of Things (IIoT) has recently attracted growing interests in the era of Industry 4.0. However, the effective detection and location of polluted areas remains a major challenge for collecting and processing a massive amount of sensor data in the IIoT especially in far sea, danger zone, and mountain zone, where there is no communication infrastructure. In this article, we establish a satellite-terrestrial framework to detect and locate industrial pollution areas by integrating the satellite with the IIoT, and the massive amount of sensor data can be delivered to the satellite via a ground base station. Local attribute detection inspired by recent advances in graph signal processing provides a promising way for solving this problem. A subgraph can be formed by grouping the vertices with identical attributes, and these vertices can be easily separated from other vertices based on local attribute detection. In this article, new methods based on local attribute detection are proposed to detect and locate pollution areas. First, a stable wavelet statistic (SWS) is proposed by modeling the classical wavelet basis as a graph-based wavelet basis. To improve the generalization ability of the SWS, a new cluster center discovery method is proposed to minimize the distance between any vertex and the remaining vertices of the same cluster. Second, a smooth scan statistic is proposed by introducing a new constraint to simplify the problem formulation of the likelihood ratio test. The effectiveness of the two graph-based statistical methods is evaluated using real datasets for detecting and locating industrial pollution.