LARGE SPARSE KERNELS FOR FEDERATED LEARNING

Feilong Zhang; Yinchuan Li; Shiyi Lin; Yunfeng Shao; Junjun Jiang; Xianming Liu

LARGE SPARSE KERNELS FOR FEDERATED LEARNING

Feilong Zhang
, Yinchuan Li
, Shiyi Lin
, Yunfeng Shao
, Junjun Jiang
, Xianming Liu^*

^*Corresponding author for this work

Faculty of Computing

Harbin Institute of Technology
Huawei Technologies Co., Ltd.

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

Existing approaches to address non-iid data in federated learning are often tailored to specific types of heterogeneity and may lack generalizability to all scenarios. In this paper, we present empirical evidence supporting the claim that employing large sparse convolution kernels can lead to enhanced robustness against distribution shifts in the context of federated learning for various non-iid problems, including imbalanced data volumes, different feature spaces, and label distributions. Our experimental results demonstrate that the substitution of convolutional kernels with large sparse kernels can yield substantial improvements in the ability to resist non-iid problems across multiple methods.

Original language	English
State	Published - 2023
Event	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 - Kigali, Rwanda Duration: 5 May 2023 → 5 May 2023

Conference

Conference	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Country/Territory	Rwanda
City	Kigali
Period	5/05/23 → 5/05/23

Cite this

@conference{69545e2e723c4859bf6fc9fd2525ae7d,

title = "LARGE SPARSE KERNELS FOR FEDERATED LEARNING",

abstract = "Existing approaches to address non-iid data in federated learning are often tailored to specific types of heterogeneity and may lack generalizability to all scenarios. In this paper, we present empirical evidence supporting the claim that employing large sparse convolution kernels can lead to enhanced robustness against distribution shifts in the context of federated learning for various non-iid problems, including imbalanced data volumes, different feature spaces, and label distributions. Our experimental results demonstrate that the substitution of convolutional kernels with large sparse kernels can yield substantial improvements in the ability to resist non-iid problems across multiple methods.",

author = "Feilong Zhang and Yinchuan Li and Shiyi Lin and Yunfeng Shao and Junjun Jiang and Xianming Liu",

note = "Publisher Copyright: {\textcopyright} 2023 1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023. All rights reserved.; 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 ; Conference date: 05-05-2023 Through 05-05-2023",

year = "2023",

language = "英语",

}

TY - CONF

T1 - LARGE SPARSE KERNELS FOR FEDERATED LEARNING

AU - Zhang, Feilong

AU - Li, Yinchuan

AU - Lin, Shiyi

AU - Shao, Yunfeng

AU - Jiang, Junjun

AU - Liu, Xianming

PY - 2023

Y1 - 2023

N2 - Existing approaches to address non-iid data in federated learning are often tailored to specific types of heterogeneity and may lack generalizability to all scenarios. In this paper, we present empirical evidence supporting the claim that employing large sparse convolution kernels can lead to enhanced robustness against distribution shifts in the context of federated learning for various non-iid problems, including imbalanced data volumes, different feature spaces, and label distributions. Our experimental results demonstrate that the substitution of convolutional kernels with large sparse kernels can yield substantial improvements in the ability to resist non-iid problems across multiple methods.

AB - Existing approaches to address non-iid data in federated learning are often tailored to specific types of heterogeneity and may lack generalizability to all scenarios. In this paper, we present empirical evidence supporting the claim that employing large sparse convolution kernels can lead to enhanced robustness against distribution shifts in the context of federated learning for various non-iid problems, including imbalanced data volumes, different feature spaces, and label distributions. Our experimental results demonstrate that the substitution of convolutional kernels with large sparse kernels can yield substantial improvements in the ability to resist non-iid problems across multiple methods.

UR - https://www.scopus.com/pages/publications/105026749981

M3 - 论文

AN - SCOPUS:105026749981

T2 - 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023

Y2 - 5 May 2023 through 5 May 2023

ER -

LARGE SPARSE KERNELS FOR FEDERATED LEARNING

Abstract

Conference

Other files and links

Fingerprint

Cite this