paper-with-me

홈 › Papers

MultiConfederated Learning: Inclusive Non-IID Data handling with Decentralized Federated Learning

2024-04-20 · Michael Duchesne, Kaiwen Zhang, Chamseddine Talhi

Federated Learning (FL) has emerged as a prominent privacy-preserving technique for enabling use cases like confidential clinical machine learning. FL operates by aggregating models trained by remote devices which owns the data. Thus, FL enables the training of powerful global models using crowd-sourced data from a large number of learners, without compromising their privacy. However, the aggregating server is a single point of failure when generating the global model. Moreover, the performance of the model suffers when the data is not independent and identically distributed (non-IID data) on all remote devices. This leads to vastly different models being aggregated, which can reduce the performance by as much as 50% in certain scenarios. In this paper, we seek to address the aforementioned issues while retaining the benefits of FL. We propose MultiConfederated Learning: a decentralized FL framework which is designed to handle non-IID data. Unlike traditional FL, MultiConfederated Learning will maintain multiple models in parallel (instead of a single global model) to help with convergence when the data is non-IID. With the help of transfer learning, learners can converge to fewer models. In order to increase adaptability, learners are allowed to choose which updates to aggregate from their peers.

📄 PDF Abstract BibTeX arXiv:2404.13421

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPrivacy PreservingTransfer Learning

Similar Papers 제목 키워드 기반

No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices

2022-02-16 · Ruixuan Liu, Fangzhao Wu, Chuhan Wu, Yanlin Wang 외

Federated learning (FL) is an important paradigm for training global models from decentralized data in a privacy-preserving way. Existing FL methods usually assume the global model can be trained on any participating cli…

Federated LearningKnowledge DistillationPrivacy Preserving

DFCA: Decentralized Federated Clustering Algorithm

2025-10-17 · Jonas Kirch, Sebastian Becker, Tiago Koketsu Rodrigues, Stefan Harmeling arxiv

Clustered Federated Learning has emerged as an effective approach for handling heterogeneous data across clients by partitioning them into clusters with similar or identical data distributions. However, most existing met…

Federated Learning

Post-Quantum Secure Federated DeFi for Inclusive Banking

2026-06-09 · Swati Sachan, Dale Fickett, Richard Buchinger, Theo Miller arxiv

Recent advances in error-corrected qubits have accelerated the timeline for practical quantum computing. It poses a threat to cryptographic primitives used to secure financial systems, government infrastructure, communic…

Incentivizing Inclusive Contributions in Model Sharing Markets

2025-05-05 · Enpei Zhang, Jingyi Chai, Rui Ye, Yanfeng Wang 외

While data plays a crucial role in training contemporary AI models, it is acknowledged that valuable public data will be exhausted in a few years, directing the world's attention towards the massive decentralized private…

Federated LearningInstruction FollowingmodelPersonalized Federated Learning

FedBGS: A Blockchain Approach to Segment Gossip Learning in Decentralized Systems

2026-02-01 · Fabio Turazza, Marcello Pietri, Marco Picone, Marco Mamei arxiv

Privacy-Preserving Federated Learning (PPFL) is a Decentralized machine learning paradigm that enables multiple participants to collaboratively train a global model without sharing their data with the integration of cryp…

Federated Learning