FEDERATED LEARNING FOR LOCAL AND GLOBAL DATA DISTRIBUTION

Gaurav Goswami; Akshay Agarwal; Nalini K. Ratha; Richa Singh; Mayank Vatsa

FEDERATED LEARNING FOR LOCAL AND GLOBAL DATA DISTRIBUTION

Gaurav Goswami
, Akshay Agarwal
, Nalini K. Ratha
, Richa Singh
, Mayank Vatsa

Department of Computer Science and Engineering

IBM
Indian Institute of Science Education and Research Bhopal
Indian Institute of Technology Jodhpur

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

1 Scopus citations

Abstract

Existing research in Federated Learning focuses on synthetic or small-scale datasets, with in-house distribution posing challenges for long-term real-world use cases. We propose a novel approach that maximizes in-house (local) distribution gains while focusing on generalization. Experimental results on several datasets demonstrate the efficacy of the proposed approach.

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

Conference

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

Cite this

@conference{1165ec0961c14ace9b9bc9e6c584ba85,

title = "FEDERATED LEARNING FOR LOCAL AND GLOBAL DATA DISTRIBUTION",

abstract = "Existing research in Federated Learning focuses on synthetic or small-scale datasets, with in-house distribution posing challenges for long-term real-world use cases. We propose a novel approach that maximizes in-house (local) distribution gains while focusing on generalization. Experimental results on several datasets demonstrate the efficacy of the proposed approach.",

author = "Gaurav Goswami and Akshay Agarwal and Ratha, \{Nalini K.\} and Richa Singh and Mayank Vatsa",

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 = "English",

}

TY - CONF

T1 - FEDERATED LEARNING FOR LOCAL AND GLOBAL DATA DISTRIBUTION

AU - Goswami, Gaurav

AU - Agarwal, Akshay

AU - Ratha, Nalini K.

AU - Singh, Richa

AU - Vatsa, Mayank

PY - 2023

Y1 - 2023

N2 - Existing research in Federated Learning focuses on synthetic or small-scale datasets, with in-house distribution posing challenges for long-term real-world use cases. We propose a novel approach that maximizes in-house (local) distribution gains while focusing on generalization. Experimental results on several datasets demonstrate the efficacy of the proposed approach.

AB - Existing research in Federated Learning focuses on synthetic or small-scale datasets, with in-house distribution posing challenges for long-term real-world use cases. We propose a novel approach that maximizes in-house (local) distribution gains while focusing on generalization. Experimental results on several datasets demonstrate the efficacy of the proposed approach.

UR - https://www.scopus.com/pages/publications/105026757635

M3 - Paper

AN - SCOPUS:105026757635

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

Y2 - 5 May 2023 through 5 May 2023

ER -

FEDERATED LEARNING FOR LOCAL AND GLOBAL DATA DISTRIBUTION

Abstract

Conference

Other files and links

Fingerprint

Cite this