Prototype-based Personalized Pruning

2021-03-25 · Jangho Kim, Simyung Chang, Sungrack Yun, Nojun Kwak

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.

📄 PDF Abstract BibTeX arXiv:2103.15564

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword Spotting Model Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

ProtoryNet - Interpretable Text Classification Via Prototype Trajectories

2020-07-03 · Dat Hong, Tong Wang, Stephen S. Baek

We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories. Motivated by the prototype theory in modern linguistics, ProtoryNet makes…

Classification General Classification Sentence text-classification+1

Personalized Classifier Ensemble Pruning Framework for Mobile Crowdsourcing

2017-01-25 · Shaowei Wang, Liusheng Huang, Pengzhan Wang, Hongli Xu 외

Ensemble learning has been widely employed by mobile applications, ranging from environmental sensing to activity recognitions. One of the fundamental issue in ensemble learning is the trade-off between classification ac…

Ensemble Learning Ensemble Pruning

SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport

2026-04-08 · Zheng Jiang, Nan He, Yiming Chen, Lifeng Sun arxiv

Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and statistical heterogeneity. While federated network pruning offers a path …

Personalized Federated Learning Network Pruning

Using a quantitative assessment of propulsion biomechanics in wheelchair racing to guide the design of personalized gloves: a case study

2023-09-15 · Félix Chénier, Gerald Parent, Mikaël Leblanc, Colombe Bélaise 외

This study with a T-52 class wheelchair racing athlete aimed to combine quantitative biomechanical measurements to the athlete's perception to design and test different prototypes of a new kind of rigid gloves. Three per…

FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion

2026-03-31 · Ningzhi Gao, Siquan Huang, Leyu Shi, Ying Gao arxiv

Federated prototype learning (FPL), as a solution to heterogeneous federated learning (HFL), effectively alleviates the challenges of data and model heterogeneity.However, existing FPL methods fail to balance the fidelit…

Contrastive Learning Federated Learning