Prototype-based Personalized Pruning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 25 Mar 2021.
Builds on
16 of 21 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
- 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
- 2018Paraphrasing Complex Network: Network Compression via Factor Transfercited by 255
- 2017Convolutional Networks with Adaptive Inference Graphscited by 147
- 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
- 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
- 2019Feature Fusion for Online Mutual Knowledge Distillationcited by 40
- 2019Centroid-based deep metric learning for speaker recognitioncited by 20
4 more
- 2019Query-by-example on-device keyword spottingcited by 19
- 2020An Overview of Deep Learning Architectures in Few-Shot Learning Domaincited by 16
- 2019URNet : User-Resizable Residual Networks with Conditional Gating Modulecited by 6
- 2020Position-based Scaled Gradient for Model Quantization and Pruningcited by 4
Built on by
Citing papers per year: 2021: 1.
1 paper.