RCT: Resource Constrained Training for Edge AI
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are designed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are trivial for powerful servers, but critical for edge devices. To mitigate these issues, We propose Resource Constrained Training (RCT). RCT only keeps a quantised model throughout the training, so that the memory requirements for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically in order to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image application and natural language processing. Experiments show that RCT saves more than 86\% energy for General Matrix Multiply (GEMM) and saves more than 46\% memory for model parameters, with limited accuracy loss. Comparing with QAT-based method, RCT saves about half of energy on moving model parameters.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks
The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising so…
Edge-computingFederated LearningFedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices
Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The iterative training process in conventional…
Edge-computingFederated LearningResource-Constrained Federated Continual Learning: What Does Matter?
Federated Continual Learning (FCL) aims to enable sequentially privacy-preserving model training on streams of incoming data that vary in edge devices by preserving previous knowledge while adapting to new data. Current …
Continual LearningGPUIncremental LearningPrivacy PreservingFADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices
Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems. However, the high demand for memory capacity and computing power makes large-scale …
Adversarial RobustnessFederated LearningPrivacy PreservingEdge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning mode…
Machine Unlearning