FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Bruno J.T. Fernandes
  • Agostinho Freire
  • João V R. de Andrade
  • Leandro H.S. Silva
  • Nicolás Navarro-Guerrero

Research Organisations

External Research Organisations

  • Universidade de Pernambuco
View graph of relations

Details

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings
EditorsWalter Senn, Marcello Sanguineti, Ausra Saudargiene, Igor V. Tetko, Alessandro E. P. Villa, Viktor Jirsa, Yoshua Bengio
PublisherSpringer Science and Business Media Deutschland GmbH
Pages391-403
Number of pages13
ISBN (electronic)978-3-032-04558-4
ISBN (print)9783032045577
Publication statusPublished - 12 Sept 2026
Event34th International Conference on Artificial Neural Networks, ICANN 2025 - Kaunas, Lithuania
Duration: 9 Sept 202512 Sept 2025

Publication series

NameLecture Notes in Computer Science
Volume16068 LNCS
ISSN (Print)0302-9743
ISSN (electronic)1611-3349

Abstract

Federated learning is a decentralized machine learning approach where models are trained collaboratively across multiple devices or nodes holding local data without sharing that data directly. It enables privacy-preserving, scalable, and collaborative machine learning. One of the key challenges in federated learning is its inefficiency in handling scenarios where data is highly imbalanced and non-independent and identically distributed (non-IID) across local nodes, leading to biased global models and slow convergence. This paper introduces a peer-to-peer refinement mechanism combined with FedAvg aggregation to enhance model accuracy in highly imbalanced and non-IID federated learning scenarios. Experiments were conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets using a Dirichlet distribution with α=0.1 to simulate highly imbalanced and non-IID data scenarios. The results demonstrated that the proposed approach achieved higher accuracy, 98.17% in MNIST, 84.35% in Fashion-MNIST and 67.49% in CIFAR-10 while requiring less than half the number of rounds to converge compared to traditional federated learning methods.

Keywords

    Computer vision, Federated learning, Neural networks

ASJC Scopus subject areas

Cite this

FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. / Fernandes, Bruno J.T.; Freire, Agostinho; de Andrade, João V R. et al.
Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings. ed. / Walter Senn; Marcello Sanguineti; Ausra Saudargiene; Igor V. Tetko; Alessandro E. P. Villa; Viktor Jirsa; Yoshua Bengio. Springer Science and Business Media Deutschland GmbH, 2026. p. 391-403 (Lecture Notes in Computer Science; Vol. 16068 LNCS).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Fernandes, BJT, Freire, A, de Andrade, JVR, Silva, LHS & Navarro-Guerrero, N 2026, FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. in W Senn, M Sanguineti, A Saudargiene, IV Tetko, AEP Villa, V Jirsa & Y Bengio (eds), Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings. Lecture Notes in Computer Science, vol. 16068 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 391-403, 34th International Conference on Artificial Neural Networks, ICANN 2025, Kaunas, Lithuania, 9 Sept 2025. https://doi.org/10.1007/978-3-032-04558-4_31
Fernandes, B. J. T., Freire, A., de Andrade, JV. R., Silva, L. H. S., & Navarro-Guerrero, N. (2026). FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. In W. Senn, M. Sanguineti, A. Saudargiene, I. V. Tetko, A. E. P. Villa, V. Jirsa, & Y. Bengio (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings (pp. 391-403). (Lecture Notes in Computer Science; Vol. 16068 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-032-04558-4_31
Fernandes BJT, Freire A, de Andrade JVR, Silva LHS, Navarro-Guerrero N. FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. In Senn W, Sanguineti M, Saudargiene A, Tetko IV, Villa AEP, Jirsa V, Bengio Y, editors, Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 391-403. (Lecture Notes in Computer Science). doi: 10.1007/978-3-032-04558-4_31
Fernandes, Bruno J.T. ; Freire, Agostinho ; de Andrade, João V R. et al. / FedP2PAvg : A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings. editor / Walter Senn ; Marcello Sanguineti ; Ausra Saudargiene ; Igor V. Tetko ; Alessandro E. P. Villa ; Viktor Jirsa ; Yoshua Bengio. Springer Science and Business Media Deutschland GmbH, 2026. pp. 391-403 (Lecture Notes in Computer Science).
Download
@inproceedings{8406b2a2051b43949b03ea2a62ee2d54,
title = "FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios",
abstract = "Federated learning is a decentralized machine learning approach where models are trained collaboratively across multiple devices or nodes holding local data without sharing that data directly. It enables privacy-preserving, scalable, and collaborative machine learning. One of the key challenges in federated learning is its inefficiency in handling scenarios where data is highly imbalanced and non-independent and identically distributed (non-IID) across local nodes, leading to biased global models and slow convergence. This paper introduces a peer-to-peer refinement mechanism combined with FedAvg aggregation to enhance model accuracy in highly imbalanced and non-IID federated learning scenarios. Experiments were conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets using a Dirichlet distribution with α=0.1 to simulate highly imbalanced and non-IID data scenarios. The results demonstrated that the proposed approach achieved higher accuracy, 98.17% in MNIST, 84.35% in Fashion-MNIST and 67.49% in CIFAR-10 while requiring less than half the number of rounds to converge compared to traditional federated learning methods.",
keywords = "Computer vision, Federated learning, Neural networks",
author = "Fernandes, {Bruno J.T.} and Agostinho Freire and {de Andrade}, {Jo{\~a}o V R.} and Silva, {Leandro H.S.} and Nicol{\'a}s Navarro-Guerrero",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 34th International Conference on Artificial Neural Networks, ICANN 2025, ICANN 2025 ; Conference date: 09-09-2025 Through 12-09-2025",
year = "2026",
month = sep,
day = "12",
doi = "10.1007/978-3-032-04558-4_31",
language = "English",
isbn = "9783032045577",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "391--403",
editor = "Walter Senn and Marcello Sanguineti and Ausra Saudargiene and Tetko, {Igor V.} and Villa, {Alessandro E. P.} and Viktor Jirsa and Yoshua Bengio",
booktitle = "Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings",
address = "Germany",

}

Download

TY - GEN

T1 - FedP2PAvg

T2 - 34th International Conference on Artificial Neural Networks, ICANN 2025

AU - Fernandes, Bruno J.T.

AU - Freire, Agostinho

AU - de Andrade, João V R.

AU - Silva, Leandro H.S.

AU - Navarro-Guerrero, Nicolás

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026/9/12

Y1 - 2026/9/12

N2 - Federated learning is a decentralized machine learning approach where models are trained collaboratively across multiple devices or nodes holding local data without sharing that data directly. It enables privacy-preserving, scalable, and collaborative machine learning. One of the key challenges in federated learning is its inefficiency in handling scenarios where data is highly imbalanced and non-independent and identically distributed (non-IID) across local nodes, leading to biased global models and slow convergence. This paper introduces a peer-to-peer refinement mechanism combined with FedAvg aggregation to enhance model accuracy in highly imbalanced and non-IID federated learning scenarios. Experiments were conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets using a Dirichlet distribution with α=0.1 to simulate highly imbalanced and non-IID data scenarios. The results demonstrated that the proposed approach achieved higher accuracy, 98.17% in MNIST, 84.35% in Fashion-MNIST and 67.49% in CIFAR-10 while requiring less than half the number of rounds to converge compared to traditional federated learning methods.

AB - Federated learning is a decentralized machine learning approach where models are trained collaboratively across multiple devices or nodes holding local data without sharing that data directly. It enables privacy-preserving, scalable, and collaborative machine learning. One of the key challenges in federated learning is its inefficiency in handling scenarios where data is highly imbalanced and non-independent and identically distributed (non-IID) across local nodes, leading to biased global models and slow convergence. This paper introduces a peer-to-peer refinement mechanism combined with FedAvg aggregation to enhance model accuracy in highly imbalanced and non-IID federated learning scenarios. Experiments were conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets using a Dirichlet distribution with α=0.1 to simulate highly imbalanced and non-IID data scenarios. The results demonstrated that the proposed approach achieved higher accuracy, 98.17% in MNIST, 84.35% in Fashion-MNIST and 67.49% in CIFAR-10 while requiring less than half the number of rounds to converge compared to traditional federated learning methods.

KW - Computer vision

KW - Federated learning

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=105016533353&partnerID=8YFLogxK

U2 - 10.1007/978-3-032-04558-4_31

DO - 10.1007/978-3-032-04558-4_31

M3 - Conference contribution

AN - SCOPUS:105016533353

SN - 9783032045577

T3 - Lecture Notes in Computer Science

SP - 391

EP - 403

BT - Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings

A2 - Senn, Walter

A2 - Sanguineti, Marcello

A2 - Saudargiene, Ausra

A2 - Tetko, Igor V.

A2 - Villa, Alessandro E. P.

A2 - Jirsa, Viktor

A2 - Bengio, Yoshua

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 9 September 2025 through 12 September 2025

ER -