paper-with-me

Papers

EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search

2021-11-24 · Qian Jiang, Xiaofan Zhang, Deming Chen, Minh N. Do, Raymond A. Yeh

In hardware-aware Differentiable Neural Architecture Search (DNAS), it is challenging to compute gradients of hardware metrics to perform architecture search. Existing works rely on linear approximations with limited support to customized hardware accelerators. In this work, we propose End-to-end Hardware-aware DNAS (EH-DNAS), a seamless integration of end-to-end hardware benchmarking, and fully automated DNAS to deliver hardware-efficient deep neural networks on various platforms, including Edge GPUs, Edge TPUs, Mobile CPUs, and customized accelerators. Given a desired hardware platform, we propose to learn a differentiable model predicting the end-to-end hardware performance of neural network architectures for DNAS. We also introduce E2E-Perf, an end-to-end hardware benchmarking tool for customized accelerators. Experiments on CIFAR10 and ImageNet show that EH-DNAS improves the hardware performance by an average of $1.4\times$ on customized accelerators and $1.6\times$ on existing hardware processors while maintaining the classification accuracy.

📄 PDF Abstract BibTeX arXiv:2111.12299

Code (1)

qianjiangcn/eh-dnas 공식 구현 pytorch

Tasks

BenchmarkingNeural Architecture Search

Methods 이 논문이 사용한 방법론

Gumbel Softmax 설명 없음
DNAS 설명 없음

Similar Papers 제목 키워드 기반

MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers

2023-10-27 · Tobias King, Yexu Zhou, Tobias Röddiger, Michael Beigl

Designing domain specific neural networks is a time-consuming, error-prone, and expensive task. Neural Architecture Search (NAS) exists to simplify domain-specific model development but there is a gap in the literature f…

Hardware Aware Neural Architecture SearchNeural Architecture SearchTime SeriesTime Series Classification

Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search

2023-04-11 · Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia

In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popul…

Evolutionary AlgorithmsNeural Architecture Search

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

2018-12-09 · CVPR 2019 6 · Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang 외

Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive.…

GPUImage ClassificationNeural Architecture Search

DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training

2026-01-21 · Bostan Khan, Masoud Daneshtalab arxiv

Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from ung…

Neural Architecture SearchFederated Learning

FDNAS: Improving Data Privacy and Model Diversity in AutoML

2020-11-06 · Chunhui Zhang, Yongyuan Liang, Xiaoming Yuan, Lei Cheng

To prevent the leakage of private information while enabling automated machine intelligence, there is an emerging trend to integrate federated learning and Neural Architecture Search (NAS). Although promising as it may s…

AutoMLDiversityFederated LearningMeta-Learning+1