ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022 · 18 citations · 20 references
ComputingComputer ScienceEdge ComputingMachine LearningMemoryDeep LearningEdge Artificial IntelligenceEdge DevicesFederated LearningNeural NetworksSpeech RecognitionAccuracyCommunication Cost AnalysisCommunication-efficient TrainingEdge Federated LearningOn-device Machine LearningSpeech Pattern Recognition
This paper aims to address the major challenges of Federated Learning (FL) on edge devices: limited memory and expensive communication. We propose a novel method, called Partial Variable Training (PVT), that only trains a small subset of variables on edge devices to reduce memory usage and communication cost. With PVT, we show that network accuracy can be maintained by utilizing more local training steps and devices, which is favorable for FL involving a large population of devices. According to our experiments on two state-of-the-art neural networks for speech recognition and two different datasets, PVT can reduce memory usage by up to 1.9× and communication cost by up to 593× while attaining comparable accuracy when compared with full network training.
20
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu et al. · 2018 · 25.4K citations
Speech recognition with deep recurrent neural networks
Alex Graves, Abdelrahman Mohamed, Geoffrey E. Hinton · 2013 · 8.8K citations
Librispeech: An ASR corpus based on public domain audio books
Vassil Panayotov, Guoguo Chen, Daniel Povey et al. · 2015 · 6K citations
Computing, Computer Science, English +17
Federated Learning: Strategies for Improving Communication Efficiency
Jakub Konečný, H. Brendan McMahan, Felix X. Yu et al. · arXiv (Cornell University) · 2016 · 3K citations · Full text