Forecasting financial time series is challenging due to their intrinsic nonlinearity, high volatility, and complex dependencies across temporal scales. This study introduces MSGformer, a novel hybrid architecture that integrates multi-scale graph neural networks (MSGNet) with Transformer encoders to capture both local temporal fluctuations and long-term global trends in high-frequency financial data. The MSGNet module constructs multi-scale representations using adaptive graph convolutions and intra-sequence attention, while the Transformer component enhances long-range dependency modeling via multi-head self-attention. We evaluate MSGformer on minute-level stock index data from the Chinese A-share market, including CSI 300, SSE 50, CSI 500, and SSE Composite indices. Extensive experiments demonstrate that MSGformer significantly outperforms state-of-the-art baselines (e.g., Transformer, PatchTST, Autoformer) in terms of MAE, RMSE, MAPE, and R². The results confirm that the proposed hybrid model achieves superior prediction accuracy, robustness, and generalization across various forecasting horizons, providing an effective solution for real-world financial decision-making and risk assessment.

To resolve the impact of channel uncertainties and information leakage in wireless-powered backscatter communication networks, a robust secure resource allocation algorithm with non-orthogonal multiple access is proposed. Specifically, a secure energy-efficient maximization problem with spherical uncertainties is formulated under the constraints of the maximum transmit power, the minimum secure rate, the time allocation factors, and the minimum harvested energy. Then, the original non-convex problem with channel uncertainties is transformed into a deterministic one by applying the worst-case approach and inequality transformation. In addition, the deterministic problem is converted into a convex one by using the variable relaxation method, successive convex approximation, and Dinkelbach's method. Simulation results demonstrate that the proposed algorithm has higher energy efficiency and lower outage probabilities.

Deep neural networks generally cannot gather more helpful information with limited data in image classification, resulting in poor performance. Self-distillation, as a novel knowledge distillation technique, integrates the roles of teacher and student into a single network to solve this problem. A better understanding of the efficiency of self-distillation is critical to its advancement. In this paper, we provide a new perspective: the effectiveness of self-distillation comes not only from distillation but also from the supervisory information provided by the shallow networks. At the same time, we find a barrier that limits the effectiveness of self-distillation. Based on this, reverse self-distillation is proposed. In contrast to self-distillation, the internal knowledge flow is in the opposite direction. Experimental results show that reverse self-distillation can break the barrier of self-distillation and further improve the accuracy of networks. On average, 2.8% and 3.2% accuracy boosts are observed on CIFAR100 and TinyImageNet.

Remote sensing image scene classification holds significant application value and has long been a research hotspot in remote sensing. However, remote sensing images contain diverse objects and complex backgrounds. Reducing background interference while focusing on key target regions in the images remains a challenge, which limits the potential improvement of classification accuracy. In this paper, a local image generation module (LIGM) is proposed to generate weights for the original images. The resulting local images, generated by weighting the original images, effectively focus on key target regions while suppressing background regions. Based on the LIGM, a two-stream architecture with self-distillation and local streams (SDLS) is proposed. The self-distillation stream extracts features from the original images using a convolutional neural network (CNN) and two MobileNetV2 networks. Furthermore, a multiplex-guided attention (MGA) module is introduced into this stream to facilitate cross-network attention-guided learning between the CNN and MobileNetV2 features. In the local stream, a MobileNetV2 network is employed to extract features from the local images. The classification logits produced by the two streams are fused, resulting in the final SDLS classification score. Experimental results demonstrate that SDLS achieves competitive performance on multiple datasets.

Self-distillation has been widely applied in the field of deep learning. However, the lack of interaction between the multiple shallow branches in the self-distillation framework reduces the effectiveness of self-distillation methods. To address this issue, a feature map fusion self-distillation scheme is proposed. According to the depth of the teacher model, multiple shallow branches as student models are constructed to build a self-distillation framework. Then, the feature map fusion module fuses the intermediate feature maps of each branch to enhance the interaction between the branches. Specifically, this fusion module employs a spatial enhancement module to generate attention masks for multiple feature maps, which are averaged and applied to create intermediate maps. The mean of these intermediate maps results in the final fusion feature map. The experimental findings on the CIFAR10 and CIFAR100 datasets illustrate that our proposed technique has clear advantages in increasing the classification accuracy of the deep learning models. On average, 0.7% and 2.5% accuracy boosts are observed on the CIFAR10 and CIFAR100.