TinyTL: Reduce Activations, Not Trainable Parameters for Efficient
On-Device Learning

TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning

22 July 2020

Chuang Gan

Song Han

Papers citing "TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning"

7 / 7 papers shown

Title
Dynamic Gradient Sparse Update for Edge Training I-Hsuan Li Tian-Sheuan Chang 66 1 0 23 Mar 2025
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training Haocheng Xi Han Cai Ligeng Zhu Yunfan LU Kurt Keutzer Jianfei Chen Song Han MQ 75 9 0 25 Oct 2024
Body-Area Capacitive or Electric Field Sensing for Human Activity Recognition and Human-Computer Interaction: A Comprehensive Survey Sizhen Bian Mengxi Liu Bo Zhou P. Lukowicz Michele Magno 45 12 0 11 Jan 2024
Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraint Ael Quélennec Enzo Tartaglione Pavlo Mozharovskyi Van-Tam Nguyen 31 2 0 08 Dec 2023
Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures Zirui Fu Aleksandre Avaliani M. Donato 44 1 0 25 Mar 2023
Efficient On-device Training via Gradient Filtering Yuedong Yang Guihong Li R. Marculescu 36 18 0 01 Jan 2023
Federated Learning for Internet of Things: Applications, Challenges, and Opportunities Tuo Zhang Lei Gao Chaoyang He Mi Zhang Bhaskar Krishnamachari Salman Avestimehr FedML 19 168 0 15 Nov 2021