A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Ditto: Fair and Robust Federated Learning Through Personalization
[article]
2021
arXiv
pre-print
Fairness and robustness are two important concerns for federated learning systems. ...
To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable ...
multi-task learning. ...
arXiv:2012.04221v3
fatcat:5jkshkocejeo7ggvamegas27om
Beyond federated learning: On confidentiality-critical machine learning applications in industry
2021
Procedia Computer Science
Federated machine learning frameworks, which take into account confidentiality of distributed data sources are of increasing interest in smart manufacturing. ...
In this work, first, we shed light on the nature of this arising gap between current federated learning and requirements in industrial settings. ...
Acknowledgements The research reported in this paper has been funded by the Federal Ministry for Climate Action, Environment, Energy, Mobility, Innovation and Technology (BMK), the Federal Ministry for ...
doi:10.1016/j.procs.2021.01.296
fatcat:ov3banqt4rhfbbx6hzdh3od3hu
Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning
[article]
2017
arXiv
pre-print
This hierarchical decomposition of the task allows for efficient exploration to learn policies that identify globally optimal solutions even as the number of collaborating agents increases. ...
We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. ...
We propose Federated Control with Reinforcement Learning (FCRL), a framework for combining hierarchical and multi-agent deep RL to solve multi-agent coordination problems with a semidecentralized model ...
arXiv:1712.08266v1
fatcat:k7cxwwyedfc5tl22vasi76uxny
Multi-Participant Multi-Class Vertical Federated Learning
[article]
2020
arXiv
pre-print
In this paper, we propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. ...
Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants. ...
To address this limitation, in this paper, we propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework. ...
arXiv:2001.11154v1
fatcat:zf3uzk7thvdm5dafri67mzoj7a
Generalized Task Markets for Human and Machine Computation
2010
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
We discuss challenges and opportunities for developing generalized task markets where human and machine intelligence are enlisted to solve problems, based on a consideration of the competencies, availabilities ...
We present infrastructure and methods for enlisting and guiding human and machine computation for language translation, including details about the hardness of generating plans for assigning tasks to solvers ...
Brosman for their assistance on the Lingua Mechanica project. ...
doi:10.1609/aaai.v24i1.7652
fatcat:p2khfyamj5cpdfvc2446ynzx3y
FedParking: A Federated Learning based Parking Space Estimation with Parked Vehicle assisted Edge Computing
2021
IEEE Transactions on Vehicular Technology
We extend the application of federated learning to parking management and introduce FedParking in which Parking Lot Operators (PLOs) collaborate to train a long short-term memory model for parking space ...
As a distributed learning approach, federated learning trains a shared learning model over distributed datasets while preserving the training data privacy. ...
Federated Learning for Vehicular Networks As a privacy-preserving learning approach, federated learning enables the collaborative training of a globally shared learning model without exchanging raw data ...
doi:10.1109/tvt.2021.3098170
fatcat:bdw2nh52h5hvziji4kyzn5svyu
A Proposal of a Multi-Agent System for Adapting Learning Contents to User Competences, Context and Mobile Device
2013
Research Papers. Faculty of Materials Science and Technology. Slovak University of Technology in Trnava
Because of this, this paper proposes a new multi-agent system for adapting the learning contents to the learner's competences, to the learner's context and to his/her mobile device. ...
The paper also describes in detail the prototype developed for testing the proposed design. ...
Five different agents have been designed for carrying out this task, whose work collaboratively making up a multi-agent system. ...
doi:10.2478/rput-2013-0004
fatcat:exfuh5a57facrncnmhwb5vgunu
Methods for control over learning individual trajectory
2015
IOP Conference Series: Materials Science and Engineering
A new method of controlling the learning trajectory has been developed as a dynamic model of learning trajectory control, which uses score assessment to construct a sequence of studied subjects. ...
The task of managing the student's learning trajectory is to select disciplines and tasks on the basis of the outcome's estimates of the curriculum so that the generated learning trajectory is to follow ...
a discrete multi-criteria problem, creating a significant burden on the decision maker (DMs). ...
doi:10.1088/1757-899x/91/1/012069
fatcat:w2oq4y5txjchthox62f5w37oly
Learning Resource Referencing, Search and Aggregation at the eLearning System Level
2007
European Conference on Technology Enhanced Learning
We advocate that this approach is necessary for federated search or harvesting tools to be well integrated and find meaningful learning resources that need to be repurposed and aggregated, taking in account ...
A special emphasis is put on the aggregation of resources through a graphic scenario editor and the referencing of the resources using a knowledge and competency representation. ...
For example, a Google search can be combined with a federated search service designed for learning object repositories without changing the code. • To enable a federated search service designed for the ...
dblp:conf/ectel/PaquetteM07
fatcat:4umpmczyyjaahk53kdmjk2sdxu
A Survey on Offloading in Federated Cloud-Edge-Fog Systems with Traditional Optimization and Machine Learning
[article]
2022
arXiv
pre-print
This study provides a novel federal classification between cloud, edge, and fog and presents a comprehensive research roadmap on offloading for different federated scenarios. ...
We then provide a comprehensive survey on offloading in federated systems with machine learning approaches and the lessons learned as a result of these surveys. ...
Single-agent learning is unrealistic because a federation consists of many providers who have different offloading policies. Multi-agent learning is suitable in a federated system for two reasons. ...
arXiv:2202.10628v1
fatcat:72oyy5unmbcwdn4rrnjy3t7dgu
Integrated Sensing-Communication-Computation for Edge Artificial Intelligence
[article]
2024
arXiv
pre-print
By investigating the interplay among the three modules, this article presents various kinds of ISCC schemes for federated edge learning tasks and edge AI inference tasks in both application and physical ...
However, these three modules need to compete for network resources for enhancing their own quality-of-services. ...
., the training latency for federated learning tasks and instantaneous inference accuracy for inference tasks. ...
arXiv:2306.01162v2
fatcat:wuzaegioebdrxjnlza4tutuhh4
Ontology of core data mining entities
2014
Data mining and knowledge discovery
It provides a representational framework for the description of mining structured data, and in addition provides taxonomies of datasets, data mining tasks, generalizations, data mining algorithms and constraints ...
Acknowledgments We would like to acknowledge the support of the European Commission through the project MAESTRA-Learning from Massive, Incompletely annotated, and Structured Data (Grant Number ICT-2013 ...
Algorithm for learning multi-target regression PCTs with constraints is an instance of constraint-based multi-target regression algorithm. ...
doi:10.1007/s10618-014-0363-0
fatcat:ccfbyblvnneojoquj4ig3locaa
FedFTN: Personalized Federated Learning with Deep Feature Transformation Network for Multi-institutional Low-count PET Denoising
[article]
2023
arXiv
pre-print
While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional ...
During the federated learning process, only the denoising network's weights are communicated and aggregated, while the FTN remains at the local institutions for feature transformation. ...
A complete listing of investigators can be found at: "https://ultra-low-dosepet.grand-challenge.org/Description/"
Declaration of Competing Interest The authors declare that they have no known competing ...
arXiv:2304.00570v3
fatcat:srreec3l7fajngpbup2le6rxg4
Task Offloading with Multi-Tier Computing Resources in Next Generation Wireless Networks
[article]
2022
arXiv
pre-print
More specifically, multi-tier computing systems compensate for cloud computing through task offloading and dispersing computing tasks to multi-tier nodes along the continuum from the cloud to things. ...
In this paper, we investigate key techniques and directions for wireless communications and resource allocation approaches to enable task offloading in multi-tier computing systems. ...
Further, federated learning [57] , as a distributed learning framework, always brings the following benefits for task offloading: 1) great reduction of the amount of data that must be uploaded through ...
arXiv:2205.13866v1
fatcat:kt7zx34yljfejnxoqo3zjng23i
A MILP model for an integrated project scheduling and multi-skilled workforce allocation with flexible working hours
2017
IFAC-PapersOnLine
We here present a mixed integer linear programming model that considers important real life aspects related to the flexibility in the use of human resources, such as multi skilled workers whose skill levels ...
We here present a mixed integer linear programming model that considers important real life aspects related to the flexibility in the use of human resources, such as multi-skilled workers whose skill levels ...
Wu and Sun (2005) considered learning phenomenon during workforce allocation for multi-projects, in R&D department. ...
doi:10.1016/j.ifacol.2017.08.2221
fatcat:65jqa7ziznhvviqikj6aiig56i
« Previous
Showing results 1 — 15 out of 45,973 results