Mix2FLD : downlink federated learning after uplink federated distillation with two-way mixup |
|
Author: | Oh, Seungeun1; Park, Jihong2; Jeong, Eunjeong1; |
Organizations: |
1School of Electrical and Electronic Engineering, Yonsei University, 120-749 Seoul, Korea 2School of Information Technology, Deakin University, Geelong, VIC 3220, Australia 3Samsung Research, Samsung Electronics, Seoul, Korea
4Centre for Wireless Communications, University of Oulu, 90500 Oulu, Finland (
|
Format: | article |
Version: | accepted version |
Access: | open |
Online Access: | PDF Full Text (PDF, 1 MB) |
Persistent link: | http://urn.fi/urn:nbn:fi-fe2020120399291 |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers,
2020
|
Publish Date: | 2020-12-03 |
Description: |
AbstractThis letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL. see all
|
Series: |
IEEE communications letters |
ISSN: | 1089-7798 |
ISSN-E: | 2373-7891 |
ISSN-L: | 1089-7798 |
Volume: | 24 |
Issue: | 10 |
Pages: | 2211 - 2215 |
DOI: | 10.1109/LCOMM.2020.3003693 |
OADOI: | https://oadoi.org/10.1109/LCOMM.2020.3003693 |
Type of Publication: |
A1 Journal article – refereed |
Field of Science: |
213 Electronic, automation and communications engineering, electronics |
Subjects: | |
Funding: |
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2018-0-00170, Virtual Presence in Moving Objects through 5G), Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Science and ICT(NRF-2017R1A2A2A05069810), the Academy of Finland Project MISSION, SMARTER, and the 2019 EU-CHISTERA Projects LeadingEdge and CONNECT. |
Copyright information: |
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |