Paper Abstract and Keywords |
Presentation |
2025-02-18 13:35
Effectiveness Verification of Introducing Model Merging in Federated Learning
-- Investigation from Multi-domain Image Classification Tasks -- Kenta Kubota, Reb Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
In this paper, we evaluate the effectiveness of model merging methods for federated learning, which continuously update the pre-trained models.
Model merging, which aims to build a single effective model for various tasks by combining multiple domain-specific models obtained by fine-tuning pre-trained models, has been actively studied in recent years.
Federated learning is a framework in which multiple models collaborate to learn in a data-distributed environment and is expected to be an application of model merging due to its problem setting.
However, previous studies paid little attention to the effectiveness of model merging methods for federated learning, and there is room for further investigation.
Therefore, to clarify the technical issues involved in introducing model merging to federated learning, this paper applies some methods to an image classification task in a federated learning setting and experimentally investigates the impact of model merging on the accuracy of the model. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
Model merge / Federated learning / Foundation model / / / / / |
Reference Info. |
ITE Tech. Rep., vol. 49, no. 4, ME2025-10, pp. 52-56, Feb. 2025. |
Paper # |
ME2025-10 |
Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |
ISSN |
Online edition: ISSN 2424-1970 |
Download PDF |
|
Conference Information |
Committee |
ME AIT MMS IEICE-IE IEICE-ITS SIP |
Conference Date |
2025-02-18 - 2025-02-19 |
Place (in Japanese) |
(See Japanese page) |
Place (in English) |
Hokkaido Univ. |
Topics (in Japanese) |
(See Japanese page) |
Topics (in English) |
Image Processing, etc. |
Paper Information |
Registration To |
ME |
Conference Code |
2025-02-ME-AIT-MMS-IE-ITS-SIP |
Language |
Japanese |
Title (in Japanese) |
(See Japanese page) |
Sub Title (in Japanese) |
(See Japanese page) |
Title (in English) |
Effectiveness Verification of Introducing Model Merging in Federated Learning |
Sub Title (in English) |
Investigation from Multi-domain Image Classification Tasks |
Keyword(1) |
Model merge |
Keyword(2) |
Federated learning |
Keyword(3) |
Foundation model |
Keyword(4) |
|
Keyword(5) |
|
Keyword(6) |
|
Keyword(7) |
|
Keyword(8) |
|
1st Author's Name |
Kenta Kubota |
1st Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
2nd Author's Name |
Reb Togo |
2nd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
3rd Author's Name |
Keisuke Maeda |
3rd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
4th Author's Name |
Takahiro Ogawa |
4th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
5th Author's Name |
Miki Haseyama |
5th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
6th Author's Name |
|
6th Author's Affiliation |
() |
7th Author's Name |
|
7th Author's Affiliation |
() |
8th Author's Name |
|
8th Author's Affiliation |
() |
9th Author's Name |
|
9th Author's Affiliation |
() |
10th Author's Name |
|
10th Author's Affiliation |
() |
11th Author's Name |
|
11th Author's Affiliation |
() |
12th Author's Name |
|
12th Author's Affiliation |
() |
13th Author's Name |
|
13th Author's Affiliation |
() |
14th Author's Name |
|
14th Author's Affiliation |
() |
15th Author's Name |
|
15th Author's Affiliation |
() |
16th Author's Name |
|
16th Author's Affiliation |
() |
17th Author's Name |
|
17th Author's Affiliation |
() |
18th Author's Name |
|
18th Author's Affiliation |
() |
19th Author's Name |
|
19th Author's Affiliation |
() |
20th Author's Name |
|
20th Author's Affiliation |
() |
21st Author's Name |
|
21st Author's Affiliation |
() |
22nd Author's Name |
|
22nd Author's Affiliation |
() |
23rd Author's Name |
|
23rd Author's Affiliation |
() |
24th Author's Name |
|
24th Author's Affiliation |
() |
25th Author's Name |
|
25th Author's Affiliation |
() |
26th Author's Name |
/ / |
26th Author's Affiliation |
()
() |
27th Author's Name |
/ / |
27th Author's Affiliation |
()
() |
28th Author's Name |
/ / |
28th Author's Affiliation |
()
() |
29th Author's Name |
/ / |
29th Author's Affiliation |
()
() |
30th Author's Name |
/ / |
30th Author's Affiliation |
()
() |
31st Author's Name |
/ / |
31st Author's Affiliation |
()
() |
32nd Author's Name |
/ / |
32nd Author's Affiliation |
()
() |
33rd Author's Name |
/ / |
33rd Author's Affiliation |
()
() |
34th Author's Name |
/ / |
34th Author's Affiliation |
()
() |
35th Author's Name |
/ / |
35th Author's Affiliation |
()
() |
36th Author's Name |
/ / |
36th Author's Affiliation |
()
() |
Speaker |
Author-1 |
Date Time |
2025-02-18 13:35:00 |
Presentation Time |
15 minutes |
Registration for |
ME |
Paper # |
MMS2025-10, ME2025-10, AIT2025-10, SIP2025-10 |
Volume (vol) |
vol.49 |
Number (no) |
no.4 |
Page |
pp.52-56 |
#Pages |
5 |
Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |