Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
Enhancing generalization in Federated Learning with heterogeneous data: A comparative literature review
Future Generation Computer Systems (FGCS), Volume 157, Issue CAug 2024, Pages 1–15https://doi.org/10.1016/j.future.2024.03.027AbstractFederated Learning (FL) is a collaborative training paradigm whereby a global Machine Learning (ML) model is trained using typically private and distributed data sources without disclosing the raw data. The approach paves the way for better ...
Highlights- Conduct a review of FL methods to enhance generalization with heterogeneous data.
- Propose an original taxonomy based on the mechanisms behind the reviewed methods.
- Evaluate the performance of various methods with different data-...
- research-articleMay 2024
DePAint: a decentralized safe multi-agent reinforcement learning algorithm considering peak and average constraints
Applied Intelligence (KLU-APIN), Volume 54, Issue 8Apr 2024, Pages 6108–6124https://doi.org/10.1007/s10489-024-05433-xAbstractThe domain of safe multi-agent reinforcement learning (MARL), despite its potential applications in areas ranging from drone delivery and vehicle automation to the development of zero-energy communities, remains relatively unexplored. The primary ...
- research-articleApril 2024
NRDL: Decentralized user preference learning for privacy-preserving next POI recommendation
Expert Systems with Applications: An International Journal (EXWA), Volume 239, Issue CApr 2024https://doi.org/10.1016/j.eswa.2023.122421AbstractPredicting where a user goes next in terms of his or her previously visited points of interest (POIs) is significant for facilitating users’ daily lives. Simultaneously, it must be acknowledged that the check-in and trajectory information of the ...
- research-articleMarch 2024
An enhanced gradient-tracking bound for distributed online stochastic convex optimization
AbstractGradient-tracking (GT) based decentralized methods have emerged as an effective and viable alternative method to decentralized (stochastic) gradient descent (DSGD) when solving distributed online stochastic optimization problems. Initial studies ...
- research-articleApril 2024
Dominating Set Model Aggregation for communication-efficient decentralized deep learning
Neural Networks (NENE), Volume 171, Issue CMar 2024, Pages 25–39https://doi.org/10.1016/j.neunet.2023.11.057AbstractDecentralized deep learning algorithms leverage peer-to-peer communication of model parameters and/or gradients over communication graphs among the learning agents with access to their private data sets. The majority of the studies in this area ...
Highlights- Proposing a communication-efficient protocol for decentralized learning systems.
- Finding valuable connections in the network to reduce communication overhead.
- Hybrid of federated learning and gossiping methods.
- Verifying the ...
-
- research-articleMarch 2024
Multi-task peer-to-peer learning using an encoder-only transformer model
Future Generation Computer Systems (FGCS), Volume 152, Issue CMar 2024, Pages 170–178https://doi.org/10.1016/j.future.2023.11.006AbstractPeer-to-peer (P2P) learning is a decentralized approach to organizing the collaboration between end devices known as agents. Agents contain heterogeneous data, and that heterogeneity is disrupting the convergence and accuracy of the collectively ...
Highlights- Multi-task collaboration between two distinct NLP tasks.
- Multi-task benefits by limiting communication with peers of different task.
- Strategically freezing the shared part improves consensus between agents.
- research-articleApril 2024
Decentralized and collaborative machine learning framework for IoT
- Martín González-Soto,
- Rebeca P. Díaz-Redondo,
- Manuel Fernández-Veiga,
- Bruno Fernández-Castro,
- Ana Fernández-Vilas
Computer Networks: The International Journal of Computer and Telecommunications Networking (CNTW), Volume 239, Issue CFeb 2024https://doi.org/10.1016/j.comnet.2023.110137AbstractDecentralized machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralized and collaborative machine learning framework ...
Highlights- This paper introduces an algorithm for resource-limited devices in IoT deployments.
- Two incremental learning mechanisms are proposed: a full ILVQ and a hybrid approach.
- Two sharing protocols are proposed: a random and a performance-...
- research-articleMarch 2024
FedER: Federated Learning through Experience Replay and privacy-preserving data synthesis
- Matteo Pennisi,
- Federica Proietto Salanitri,
- Giovanni Bellitto,
- Bruno Casella,
- Marco Aldinucci,
- Simone Palazzo,
- Concetto Spampinato
Computer Vision and Image Understanding (CVIU), Volume 238, Issue CJan 2024https://doi.org/10.1016/j.cviu.2023.103882AbstractIn the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data. However, recent privacy regulations hinder the possibility to share data, and ...
Highlights- Addressing major limitations of FL: presence of a central node and model homogeneity.
- Exploiting continual learning to enforce nodes’ convergence towards a shared solution.
- GAN-based privacy preserving mechanism to enable synthetic ...
- articleFebruary 2024
Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions
Engineering Applications of Artificial Intelligence (EAAI), Volume 127, Issue PAJan 2024https://doi.org/10.1016/j.engappai.2023.107166AbstractFederated learning (FL) is an approach within the realm of machine learning (ML) that allows the use of distributed data without compromising personal privacy. In FL, it becomes evident that the training data among participants frequently exhibit ...
- research-articleSeptember 2023
Distributed quantile regression in decentralized optimization
Information Sciences: an International Journal (ISCI), Volume 643, Issue CSep 2023https://doi.org/10.1016/j.ins.2023.119259AbstractWhen dealing with massive data that is distributed across multiple servers, it is particularly important to solve the distributed learning problem while minimizing the communication cost between servers. In this paper, we investigate ...
Highlights- We introduce a novel method GPADMMQR to solve the distributed QR problem in a decentralized manner.
- research-articleAugust 2023
Robust communication-efficient decentralized learning with heterogeneity
Journal of Systems Architecture: the EUROMICRO Journal (JOSA), Volume 141, Issue CAug 2023https://doi.org/10.1016/j.sysarc.2023.102900AbstractIn this paper, we propose a robust communication-efficient decentralized learning algorithm, named RCEDL, to address data heterogeneity, communication heterogeneity and communication efficiency simultaneously in real-world scenarios. ...
- research-articleJune 2023
Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
Machine Language (MALE), Volume 112, Issue 8Aug 2023, Pages 2791–2819https://doi.org/10.1007/s10994-023-06345-6AbstractFederated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian approaches to learning benefit from offering more information as to the ...
- research-articleApril 2023
Robust decentralized stochastic gradient descent over unstable networks
Computer Communications (COMS), Volume 203, Issue CApr 2023, Pages 163–179https://doi.org/10.1016/j.comcom.2023.02.025AbstractDecentralized learning is essential for large-scale deep learning due to its great advantage in breaking the communication bottleneck. Most decentralized learning algorithms focus on reducing the communication overhead without taking into account ...
- research-articleMarch 2023
Peer-to-peer deep learning with non-IID data
Expert Systems with Applications: An International Journal (EXWA), Volume 214, Issue CMar 2023https://doi.org/10.1016/j.eswa.2022.119159AbstractCollaborative training of deep neural networks using edge devices has attracted substantial research interest recently. The two main architecture approaches for the training process are centrally orchestrated Federated Learning and ...
Highlights- Batch Normalization layers improve decentralized learning on non-IID data.
- P2P-...
- research-articleFebruary 2023
A decentralized learning strategy to restore connectivity during multi-agent formation control
Neurocomputing (NEUROC), Volume 520, Issue CFeb 2023, Pages 33–45https://doi.org/10.1016/j.neucom.2022.11.054AbstractIn this paper, we propose a decentralized learning algorithm to restore communication connectivity during multi-agent formation control. The time-varying connectivity profile of a mobile multi-agent system represents the dynamic ...
- research-articleNovember 2022
Federated learning review: Fundamentals, enabling technologies, and future applications
Information Processing and Management: an International Journal (IPRM), Volume 59, Issue 6Nov 2022https://doi.org/10.1016/j.ipm.2022.103061AbstractFederated Learning (FL) has been foundational in improving the performance of a wide range of applications since it was first introduced by Google. Some of the most prominent and commonly used FL-powered applications are Android’s ...
Highlights- Draw the big picture of the fundamental of federated machine learning.
- ...
- ArticleSeptember 2022
Cluster Based Secure Multi-party Computation in Federated Learning for Histopathology Images
Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global HealthSep 2022, Pages 110–118https://doi.org/10.1007/978-3-031-18523-6_11AbstractFederated learning (FL) is a decentralized method enabling hospitals to collaboratively learn a model without sharing private patient data for training. In FL, participant hospitals periodically exchange training results rather than training ...
- research-articleMarch 2022
Fast-DRD: Fast decentralized reinforcement distillation for deadline-aware edge computing
Information Processing and Management: an International Journal (IPRM), Volume 59, Issue 2Mar 2022https://doi.org/10.1016/j.ipm.2021.102850AbstractEdge computing has recently gained momentum as it provides computing services for mobile devices through high-speed networks. In edge computing system optimization, deep reinforcement learning(DRL) enhances the quality of services(QoS) ...
Highlights- As far as we know, Fast-DRD is the first to investigate Dec-POMDP for modeling the deadline-aware offloading problem. Fast-DRD drives a distributed ...
- research-articleJanuary 2022
An explainable semi-personalized federated learning model
Integrated Computer-Aided Engineering (ICAE), Volume 29, Issue 42022, Pages 335–350https://doi.org/10.3233/ICA-220683Training a model using batch learning requires uniform data storage in a repository. This approach is intrusive, as users have to expose their privacy and exchange sensitive data by sending them to central entities to be preprocessed. Unlike the ...
- ArticleDecember 2021
Fog Enabled Distributed Training Architecture for Federated Learning
AbstractThe amount of data being produced at every epoch of second is increasing every moment. Various sensors, cameras and smart gadgets produce continuous data throughout its installation. Processing and analyzing raw data at a cloud server faces ...