DGL: Device Generic Latency Model for Neural Architecture Search on Mobile Devices

The low-cost Neural Architecture Search (NAS) for lightweight networks working on massive mobile devices is essential for fast-developing ICT technology. Current NAS work can not search on unseen devices without latency sampling, which is a big obstacle to the implementation of NAS on mobile devices...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on mobile computing 2024-02, Vol.23 (2), p.1954-1967
Main Authors: Wang, Qinsi, Zhang, Sihai
Format: Magazinearticle
Language:English
Subjects:
Accuracy
Analytical models
Computer architecture
Configurations
Costs
Electronic devices
Hardware
latency prediction
Low cost
Mathematical models
Microprocessors
mobile devices
Mobile handsets
Network latency
Neural architecture search (NAS)
Parameters
Predictive models
processor interval analysis
Sampling
Searching
Training
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The low-cost Neural Architecture Search (NAS) for lightweight networks working on massive mobile devices is essential for fast-developing ICT technology. Current NAS work can not search on unseen devices without latency sampling, which is a big obstacle to the implementation of NAS on mobile devices. In this paper, we overcome this challenge by proposing the Device Generic Latency (DGL) model. By absorbing processor modeling technology, the proposed DGL formula maps the parameters in the interval theory to the seven static configuration parameters of the device. And to make the formula more practical, we refine it to low-cost form by decreasing the number of configuration parameters to four. Then based on this formula, the DGL model is proposed which introduces the network parameters predictor and accuracy predictor to work with the DGL formula to predict the network latency. We propose the DGL-based NAS framework to enable fast searches without latency sampling. Extensive experiments results validate that the DGL model can achieve more accurate latency predictions than existing NAS latency predictors on unseen mobile devices. When configured with current state-of-the-art predictors, DGL-based NAS can search for architectures with higher accuracy that meet the latency limit than other NAS implementations, while using less training time and prediction time. Our work shed light on how to adopt domain knowledge into NAS topic and play important role in low-cost NAS on mobile devices.
ISSN:1536-1233
1558-0660
DOI:10.1109/TMC.2023.3244170