paper-with-me

Papers

FedMef: Towards Memory-efficient Federated Dynamic Pruning

2024-03-21 · CVPR 2024 1 · Hong Huang, Weiming Zhuang, Chen Chen, Lingjuan Lyu

Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train deep learning models. Neural network pruning techniques, such as dynamic pruning, could enhance model efficiency, but directly adopting them in FL still poses substantial challenges, including post-pruning performance degradation, high activation memory usage, etc. To address these challenges, we propose FedMef, a novel and memory-efficient federated dynamic pruning framework. FedMef comprises two key components. First, we introduce the budget-aware extrusion that maintains pruning efficiency while preserving post-pruning performance by salvaging crucial information from parameters marked for pruning within a given budget. Second, we propose scaled activation pruning to effectively reduce activation memory footprints, which is particularly beneficial for deploying FL to memory-limited devices. Extensive experiments demonstrate the effectiveness of our proposed FedMef. In particular, it achieves a significant reduction of 28.5% in memory footprint compared to state-of-the-art methods while obtaining superior accuracy.

📄 PDF Abstract BibTeX arXiv:2403.14737

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices

2024-05-08 · Pengyu Zhang, Yingjie Liu, Yingbo Zhou, Xiao Du 외

Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, vari…

Federated Learning

Distributed Pruning Towards Tiny Neural Networks in Federated Learning

2022-12-05 · Hong Huang, Lan Zhang, Chaoyue Sun, Ruogu Fang 외

Neural network pruning is an essential technique for reducing the size and complexity of deep neural networks, enabling large-scale models on devices with limited resources. However, existing pruning approaches heavily r…

Federated LearningNetwork Pruning

FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization

2023-09-13 · Qianyu Long, Christos Anagnostopoulos, Shameem Puthiya Parambath, Daning Bi

Federated Learning (FL) has been successfully adopted for distributed training and inference of large-scale Deep Neural Networks (DNNs). However, DNNs are characterized by an extremely large number of parameters, thus, y…

Federated Learning

A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning

2026-03-23 · Emmanouil M. Athanasakos arxiv

Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnitude pruning effectively reduces the communication payload, i…

Federated Learning

CA-AFP: Cluster-Aware Adaptive Federated Pruning

2026-03-02 · Om Govind Jha, Harsh Shukla, Haroon R. Lone arxiv

Federated Learning (FL) faces major challenges in real-world deployments due to statistical heterogeneity across clients and system heterogeneity arising from resource-constrained devices. While clustering-based approach…

Human Activity RecognitionFederated Learning