Prototype-based Personalized Pruning

03/25/2021
by   Jangho Kim, et al.
0

Nowadays, as edge devices such as smartphones become prevalent, there are increasing demands for personalized services. However, traditional personalization methods are not suitable for edge devices because retraining or finetuning is needed with limited personal data. Also, a full model might be too heavy for edge devices with limited resources. Unfortunately, model compression methods which can handle the model complexity issue also require the retraining phase. These multiple training phases generally need huge computational cost during on-device learning which can be a burden to edge devices. In this work, we propose a dynamic personalization method called prototype-based personalized pruning (PPP). PPP considers both ends of personalization and model efficiency. After training a network, PPP can easily prune the network with a prototype representing the characteristics of personal data and it performs well without retraining or finetuning. We verify the usefulness of PPP on a couple of tasks in computer vision and Keyword spotting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/25/2021

PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation

As edge devices become prevalent, deploying Deep Neural Networks (DNN) o...
research
06/13/2021

Adaptive Dynamic Pruning for Non-IID Federated Learning

Federated Learning (FL) has emerged as a new paradigm of training machin...
research
11/30/2020

Robust error bounds for quantised and pruned neural networks

With the rise of smartphones and the internet-of-things, data is increas...
research
01/22/2022

Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer

Deep learning models have introduced various intelligent applications to...
research
10/10/2017

The Case for a Single System Image for Personal Devices

Computing technology has gotten cheaper and more powerful, allowing user...
research
08/04/2022

Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers

Keyword spotting (KWS) is beneficial for voice-based user interactions w...
research
03/22/2023

Edge Deep Learning Model Protection via Neuron Authorization

With the development of deep learning processors and accelerators, deep ...

Please sign up or login with your details

Forgot password? Click here to reset