.png){kind=icon}
返回
Model Compression for Communication Efficient Federated Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3131614.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Despite the many advantages of using deep neural networks over shallow networks in various machine learning tasks, their effectiveness is compromised in a federated learning setting due to large storage sizes and high computational resource requirements for training. A large model size can potentially require infeasible amounts of data to be transmitted between the server and clients for training. To address these issues, we investigate the traditional and novel compression techniques to construct sparse models from dense networks whose storage and bandwidth requirements are significantly lower. We do this by separately considering compression techniques for the server model to address downstream communication and the client models to address upstream communication. Both of these play a crucial role in developing and maintaining sparsity across communication cycles. We empirically demonstrate the efficacy of the proposed schemes by testing their performance on standard datasets and verify that they outperform various state-of-the-art baseline schemes in terms of accuracy and communication volume.
Keyword:
Communication efficiency
deep learning (DL)
federated learning (FL)
model compression
two-time-scale algorithms
期刊
IF:
8.9
论文数:
7.5K
被引数:
7.2W
机构
暂无机构信息
引用论文
A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Federated Learning: A Survey on Enabling Technologies, Protocols, and ApplicationsIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Heterogeneous Feature Selection With Multi-Modal Deep Neural Networks and Sparse Group LASSO基于多模态深度神经网络和稀疏组LASSO的异构特征选择OAAI
OAAI分享收藏
查看更多内容