Lingzhao Meng

FedUP: Uncertainty-Aware Personalized Federated Learning via Probabilistic Prototypes

Furui Qi, Weishan Zhang, Lingzhao Meng, Yuru Liu et autres

Prototype-based federated learning enables efficient knowledge sharing by exchanging class prototypes rather than full model parameters. However, heterogeneous client data and limited local samples increase prototype estimation variance, making many client prototypes unreliable. Existing methods usually treat prototypes as deterministic point estimates …

cn (code pays fourni par la source)

OIAFed: All-in-One Federated Learning Framework

Tao Chen, Linbo Zhou, Baoyu Zhang, Yuru Liu et autres

cn (code pays fourni par la source)

An Adaptive Federated Service Evolution Framework for Industrial Operations Analytics Under Dynamic Participation

Daobin Luo, Yuru Liu, Weishan Zhang, Yuange Liu et autres

cn (code pays fourni par la source)

Dual-level self-adaptive threshold learning for semi-supervised CNV classification

Jie Guo, Lingzhao Meng, Jia Han, ying guo et autres

cn, gr (code pays fourni par la source)

Personalized Federated Learning with Hierarchical Two-Branch Aggregation for Few-Shot Scenarios

Yifan Miao, Weishan Zhang, Yue Wang, Yi Liu et autres

Personalized federated learning (pFL) aims to address data heterogeneity by training client-specific models. However, it faces two critical challenges under few-shot conditions. First, existing methods often overlook the hierarchical structure of neural representations, limiting their ability to balance generalization and personalization. Second, …

cn (code pays fourni par la source)

Difficulty-Aware Pseudo-Label Correction Network for Fine-Grained Classification of Choroidal Neovascularization in OCT Images

Lingzhao Meng, Xiaoming Xi, Jia Han, Lishan Qiao et autres

Choroidal neovascularization (CNV) classification is a fine-grained classification task. Accurate classification of CNV in optical coherence tomography (OCT) images is crucial for clinical treatment. However, image acquisition noise degrades image quality and exacerbates confirmation bias from class imbalance in medical datasets. Moreover, …

cn (code pays fourni par la source)

Brain-Inspired Parallel Data Intelligence: a Generality-Specificity Fused Approach

Lingzhao Meng, Weishan Zhang, Fulong Xu, Liang Han et autres

Complex systems face incomplete data challenges due to privacy constraints, as well as difficulties in balancing generalization and personalized adaptation in cognitive models. Based on brain cognitive mechanisms and parallel systems theory, we propose the brain-inspired parallel data intelligence approach that fuses …

cn (code pays fourni par la source)

Toward Accurate Federated Graph Learning Via Layer-Wised Clustering for Social Internet of Things

Yuru Liu, Yuange Liu, Weishan Zhang, Qiao Qiao et autres

federated graph learning (FGL) has emerged as a promising paradigm for privacy-preserving collaborative learning in Social Internet of Things (SIoT), where nodes form complex interconnected networks. Existing FGL approaches face significant challenges including model degradation in handling nonindependent and identically distributed (non-IID) …

cn (code pays fourni par la source)

Semi-supervised Adaptive Weighted Network for CNV Typing in OCT Images

Lingzhao Meng, Xiaoming Xi, Meixia Wang, Tianming Tan et autres

Choroidal neovascularization (CNV) is a wet age-related macular degeneration (AMD), which will seriously affect the vision of patients. Accurate CNV typing in OCT images plays an important auxiliary role in disease treatment. However, large number of noises may be introduced due to …

cn (code pays fourni par la source)

Triple-attention interaction network for breast tumor classification based on multi-modality images

Xiao Fang Yang, Xiaoming Xi, Kesong Wang, Liangyun Sun et autres

cn (code pays fourni par la source)

Attention-based Interactions Network for Breast Tumor Classification with Multi-modality Images

Xiao Hui Yang, Xiaoming Xi, Chuanzhen Xu, Liangyun Sun et autres

Benefiting from the development of medical imaging, the automatic breast image classification has been extensively studied in a variety of breast cancer diagnosis tasks recently. The multi-modality image fusion was helpful to further improve classification performance. However, existing multi-modality fusion methods focused …

cn (code pays fourni par la source)

Local Detail Enhancement Network for CNV Typing in OCT Images

Chuanzhen Xu, Xiaoming Xi, Xiao Fang Yang, Liangyun Sun et autres

Choroidal neovascularization (CNV) is one of the severe eye disease. The severe results will cause of loss of acuity, scotomata, and distortion of vision. Automatic and accurate classification of CNV with optical coherence tomography (OCT) images can assist doctors in treatment. However, …

cn (code pays fourni par la source)