.png){kind=icon}
返回
An Elastic Federated Learning Collaboration Framework for Computing-Constrained IoT
.png){kind=icon}
PRE
AI
DOI：10.1109/TCAD.2025.3593436.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Through exploiting decentralized data from multisource Internet of Things (IoT) devices, federated learning (FL) can accomplish the training of deep neural network (DNN) models in a privacy-preserving manner to provide premium intelligent services. Due to portability considerations, most IoT devices are computing-constrained which cannot afford frequent DNN model training in FL. Existing approaches use model compression techniques to reduce computing cost of IoT devices, whereas accuracy degradation is inevitably incurred. To address this challenge, we propose an elastic FL collaboration framework (EFLCF), namely, EFLCF, to accommodate limited computing resources of IoT devices. Specifically, we first design an FL-oriented elastic neural network model with multiple-width subnets, and couple it with an FL device-server collaboration framework to form EFLCF, thereby releasing computing cost pressure of IoT devices. We then develop a freezing-assisted wide-to-narrow training mechanism to realize efficient device-server distributed training and further reduce device computing cost. Finally, we design an entropy-based narrow-to-wide elastic inference mechanism to decrease computing cost of inference without compromising accuracy. Experiments demonstrate that compared to well-known benchmarks, our EFLCF can reduce up to 97.65% device computing cost and improve up to 48.3% accuracy in training, while reducing up to 42.5% computing cost in inference.
Keyword:
Computing cost
federated learning (FL)
inference mechanism
Internet of Things (IoT)
training mechanism
期刊
I
IF:
2.9
论文数:
606
被引数:
9.6K
机构
引用论文
.png){kind=icon}
分享收藏A Lightweight and Adaptive Knowledge Distillation Framework for Remaining Useful Life Prediction用于剩余使用寿命预测的轻量级自适应知识蒸馏框架
PREAI
分享收藏Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation具有分层异步模型更新和时间加权聚合的高效通信联合深度学习
OAAI
OAAI分享收藏JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing ServicesOAAI
OAAI分享收藏分享收藏分享收藏
查看更多内容