Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/165563
Title: Collate: collaborative neural network learning for latency-critical edge systems
Authors: Huai, Shuo
Liu, Di
Kong, Hao
Luo, Xiangzhong
Liu, Weichen
Subramaniam, Ravi
Makaya, Christian
Lin, Qian
Keywords: Engineering::Computer science and engineering::Software
Issue Date: 2022
Source: Huai, S., Liu, D., Kong, H., Luo, X., Liu, W., Subramaniam, R., Makaya, C. & Lin, Q. (2022). Collate: collaborative neural network learning for latency-critical edge systems. 2022 IEEE 40th International Conference on Computer Design (ICCD), 627-634. https://dx.doi.org/10.1109/ICCD56317.2022.00097
Project: I1801E0028
Conference: 2022 IEEE 40th International Conference on Computer Design (ICCD)
Abstract: Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a severe impact on the performance of the inferred model. Existing optimizations on FL focus on improving the training efficiency but fail to speed up inference, especially when there is a latency constraint. In this work, we propose Collate, a novel training framework that collaboratively learns heterogeneous models to meet the latency constraints of multiple edge systems simultaneously. We design a dynamic zeroizing-recovering method to adjust each local model architecture for high accuracy under its latency constraint. A proto-corrected federated aggregation scheme is also introduced to aggregate all heterogeneous local models, satisfying the latency constraint of different systems with only one training process and maintaining high accuracy. Extensive experiments indicate that, compared to state-of-the-art methods and under a latency constraint, our extended models can improve the accuracy by 1.96% on average, and our shrunk models can also obtain a 3.09% accuracy improvement on average, with almost no extra training overhead. The related codes and data will be available at https://github.com/ntuliuteam/Collate.
URI: https://hdl.handle.net/10356/165563
DOI: 10.1109/ICCD56317.2022.00097
Schools: School of Computer Science and Engineering 
Research Centres: HP-NTU Digital Manufacturing Corporate Lab
Rights: © 2022 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Conference Papers

SCOPUSTM   
Citations 50

1
Updated on May 18, 2024

Page view(s)

145
Updated on May 19, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.