Institution profile

Xidian University

Academic institutionasia · cn
Official website
Research library1,087linked papers
Opportunities0open roles
Selected work

Representative Papers

FedBCGD: Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning

Oct 28, 2024ACM Multimedia

This work addresses the high communication overhead of large-scale models, such as Vision Transformers, in federated learning by proposing Federated Block Coordinate Gradient Descent (FedBCGD) and its accelerated variant, FedBCGD+. The method introduces, for the first time in federated learning, a block-wise parameter communication mechanism that uploads only a subset of parameter blocks per round, combined with stochastic variance reduction and client drift control strategies. Theoretical analysis shows that the communication complexity is reduced by a factor of 1/N compared to existing methods, where N denotes the number of blocks. Experimental results demonstrate that the proposed algorithms achieve faster convergence and higher communication efficiency than current state-of-the-art approaches.

37 citations2 influentialRead paper

Multiview Point Cloud Registration Based on Minimum Potential Energy for Free-Form Blade Measurement

Feb 11, 2025IEEE Transactions on Instrumentation and Measurement

In industrial metrology, global registration of multi-view point clouds from freeform turbine blades suffers from low accuracy due to severe noise and substantial data incompleteness. To address this, this paper proposes a novel Minimum Potential Energy (MPE)-based registration method. It innovatively introduces a physical potential energy model into point cloud registration, formulating a weighted MPE optimization objective. A dual-flag mechanism is designed to dynamically assess registration status, while a coarse-to-fine strategy enhances robustness and convergence. Furthermore, a force-guided operator and an improved TrICP algorithm are introduced. Experiments on four real-world blade datasets demonstrate that the proposed method achieves higher registration accuracy and superior noise resilience compared to state-of-the-art global registration approaches, significantly improving the reliability and practicality of industrial-grade freeform surface reconstruction.

16 citationsRead paper

Consistency of Local and Global Flatness for Federated Learning

Oct 27, 2025ACM Multimedia

This work addresses the challenge in federated learning where multiple local updates under data heterogeneity often drive the global model toward sharp minima, degrading generalization. Existing sharpness-aware methods struggle to align local and global flatness. To this end, we propose FedNSAM, an algorithm that leverages global Nesterov momentum to guide local updates, constructing an estimated direction of global perturbation and performing extrapolation to harmonize local and global flatness. We introduce a novel “flatness distance” metric to quantify the inconsistency between local and global landscapes and establish a tighter convergence bound than FedSAM in our theoretical analysis. Empirical results demonstrate that FedNSAM significantly enhances both generalization performance and training efficiency across CNN and Transformer architectures, particularly in highly heterogeneous settings.

11 citationsRead paper

CL-CaGAN: Capsule Differential Adversarial Continual Learning for Cross-Domain Hyperspectral Anomaly Detection

May 17, 2025IEEE Transactions on Geoscience and Remote Sensing

Addressing the dual challenges of scarce prior knowledge in cross-domain hyperspectral anomaly detection and catastrophic forgetting in continual learning, this paper proposes a differentiable generative adversarial continual learning framework based on capsule networks. Methodologically, it introduces the first end-to-end integration of capsule architectures with generative adversarial networks; designs a clustering-driven sample replay mechanism coupled with self-distillation regularization; and incorporates differentiable data augmentation to enhance robustness in background modeling. Extensive experiments on multiple real-world hyperspectral datasets demonstrate that the proposed method significantly improves cross-domain detection accuracy, effectively mitigates forgetting, strengthens background reconstruction fidelity and anomaly discrimination capability, and yields more stable training dynamics compared to existing approaches.

8 citationsRead paper

Attention-Based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Feb 01, 2023IEEE Internet of Things Journal

Lightweight Transformers for wireless modulation classification on IoT devices suffer from vulnerability to adversarial attacks—particularly cross-architecture transfer attacks—while struggling to balance robustness and inference efficiency. Method: This paper proposes an attention-mechanism-transfer-based adversarial robust knowledge distillation framework. It distills robust attention maps learned by a large teacher model during adversarial training into a compact Transformer student, without incurring additional inference overhead. The approach integrates adversarial training, attention-guided knowledge distillation, and lightweight architecture design. Contribution/Results: Under FGSM and PGD white-box attacks, the distilled lightweight model achieves significantly enhanced robustness and effectively mitigates adversarial sample transfer across architectures. Experiments demonstrate high-accuracy, robust modulation classification under resource constraints—retaining low latency and power consumption—thus overcoming the critical bottleneck of co-optimizing model lightness and security.

7 citationsRead paper
Recent publications

Latest Papers