paper-with-me

Papers

Exploiting Label Skewness for Spiking Neural Networks in Federated Learning

2024-12-23 · Di Yu, Xin Du, Linshan Jiang, Huijing Zhang, Shunwen Bai, Shuiguang Deng

The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To address data privacy concerns when deploying SNNs on edge devices, federated learning (FL) facilitates collaborative model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches struggle with label-skewed data across devices, which leads to drift in local SNN models and degrades the performance of the global SNN model. In this paper, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.

📄 PDF Abstract BibTeX arXiv:2412.17305

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningKnowledge DistillationMissing Labels

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
SNN Spiking Neural Networks (SNNs) are a class of artificial neural networks inspired by the structure and functioning of the brain's neural networks. Unlike traditional…

Similar Papers 제목 키워드 기반

FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving

2023-09-23 · Eros Fanì, Marco Ciccone, Barbara Caputo

We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across …

Autonomous DrivingDomain GeneralizationFederated LearningSegmentation+2

CalFAT: Calibrated Federated Adversarial Training with Label Skewness

2022-05-30 · Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu

Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks. To improve the adversarial robustness of FL, federated adversarial training (FAT) meth…

Adversarial RobustnessFederated Learning

BOBA: Byzantine-Robust Federated Learning with Label Skewness

2022-08-27 · Wenxuan Bao, Jun Wu, Jingrui He

In federated learning, most existing robust aggregation rules (AGRs) combat Byzantine attacks in the IID setting, where client data is assumed to be independent and identically distributed. In this paper, we address labe…

Federated LearningSelection bias

Towards Practical Few-shot Federated NLP

2022-12-01 · Dongqi Cai, Yaozong Wu, Haitao Yuan, Shangguang Wang 외

Transformer-based pre-trained models have emerged as the predominant solution for natural language processing (NLP). Fine-tuning such pre-trained models for downstream tasks often requires a considerable amount of labele…

Data AugmentationFederated LearningFew-Shot Learning

FedSat: A Statistical Aggregation Approach for Class Imbalanced Clients in Federated Learning

2024-07-04 · Sujit Chowdhury, Raju Halder

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed machine learning, but faces challenges with heterogeneous data distributions across clients. This paper presents FedSat, a no…

Federated LearningPrivacy Preserving