CFL: Cluster Federated Learning in Large-Scale Peer-to-Peer Networks

Chen, Qian; Wang, Zilong; Zhou, Yifei; Chen, Jiawei; Xiao, Dingquan; Lin, Xiaodong

doi:10.1007/978-3-031-22390-7_27

Cited by 4 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 5a shows how the code length evolves as the number of the parameters increases. We compared the expected code length of the proposed Elias coding for FedLP-Q (as in (18)), the Elias coding for QSGD (as in (19)), and the non-quantization coding (Float32). For a parameter count of less than 600 K, the Elias-based coding scheme proposed in Section 3.2.2 led to the lowest expected code length.…”

Section: Resultsmentioning

confidence: 99%

“…For example, Horvath et al pointed out that the order of the parameters matters in pruning aggregation and should be taken into consideration [17]. Depth-wise schemes based on blocks and layers were also discussed in [18,19], which showed that model compression in FL should affects the functionality of different parts in local models. The FedLP schemes in [19] specifically provided common pruning solutions for model heterogeneity cases, which extends the FL scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…Consider the code blocks of the l-th layer as shown in Figure 2, the code length can be divided into three parts: (1) The first block to represent the layer 2-norm g l k 2 takes 32 bits; (2) the Elias codes of the quantization level b takes 1 + (1 + o(1)) log b bits; and (3) after stochastic quantization, the interval index of each parameter is an integer less than 2 b , which takes 1 + (1 + o(1))b bits, and its sign takes one more bit. Hence, the total code length can be upper bounded as shown in (18).…”

Section: Coding Performancementioning

confidence: 99%

See 2 more Smart Citations

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design

Zhu

Shi

Xin

et al. 2023

Entropy

View full text Add to dashboard Cite

As a promising distributed learning paradigm, federated learning (FL) faces the challenge of communication–computation bottlenecks in practical deployments. In this work, we mainly focus on the pruning, quantization, and coding of FL. By adopting a layer-wise operation, we propose an explicit and universal scheme: FedLP-Q (federated learning with layer-wise pruning-quantization). Pruning strategies for homogeneity/heterogeneity scenarios, the stochastic quantization rule, and the corresponding coding scheme were developed. Both theoretical and experimental evaluations suggest that FedLP-Q improves the system efficiency of communication and computation with controllable performance degradation. The key novelty of FedLP-Q is that it serves as a joint pruning-quantization FL framework with layer-wise processing and can easily be applied in practical FL systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Coding Performancementioning

confidence: 99%

See 1 more Smart Citation

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design

Zhu

Shi

Xin

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…To demonstrate the accelerated intra-subgraph propagation process facilitated by AST in the IoV environment, a comparison is drawn with propagation patterns in the PPT algorithm [16] and the CFL algorithm [17]. Both algorithms are grounded in P2P-mode federated learning and employ a single-line propagation mode of depth-first traversal.…”

Section: Aggregated Simultaneous Transmissionmentioning

confidence: 99%

P2P Federated Learning Based on Node Segmentation with Privacy Protection for IoV

Zhao,

Guo,

Yang

et al. 2024

Electronics

View full text Add to dashboard Cite

The current usage of federated learning in applications relies on the existence of servers. To address the inability to conduct federated learning for IoV (Internet of Vehicles) applications in serverless areas, a P2P (peer-to-peer) architecture for federated learning is proposed in this paper. Following node segmentation based on limited subgraph diameters, an edge aggregation mode is employed to propagate models inwardly, and a mode for propagating the model inward to the C-node (center node) while aggregating is proposed. Simultaneously, a personalized differential privacy scheme was designed under this architecture. Through experimentation and verification, the approach proposed in this paper demonstrates the combination of both security and usability.

show abstract

Adaptive Model Aggregation for Decentralized Federated Learning in Vehicular Networks

Movahedian,

Dolati,

Ghaderi

2023

2023 19th International Conference on Network and Service Management (CNSM)

View full text Add to dashboard Cite

CFL: Cluster Federated Learning in Large-Scale Peer-to-Peer Networks

Cited by 4 publications

References 5 publications

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design

P2P Federated Learning Based on Node Segmentation with Privacy Protection for IoV

Adaptive Model Aggregation for Decentralized Federated Learning in Vehicular Networks

Contact Info

Product

Resources

About