A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf
.
Filters
Federated Learning as a Network Effects Game
[article]
2023
arXiv
pre-print
We are the first to model clients' behaviors in FL as a network effects game, where each client's benefit depends on other clients who also join the network. ...
Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data. ...
Morgan Faculty Award, a Facebook Research Award, and a Mozilla Research Grant. ...
arXiv:2302.08533v1
fatcat:mgabqgfrwbdrdogeiycbjwwqnu
Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism
[article]
2020
arXiv
pre-print
We model the incentive-based interaction between a global server and participating devices for federated learning via a Stackelberg game to motivate the participation of the devices in the federated learning ...
Federated learning can be a promising solution for enabling IoT-based smart applications. In this paper, we present the primary design aspects for enabling federated learning at network edge. ...
FEDERATED LEARNING AT THE EDGE: KEY DESIGN ASPECTS
A. ...
arXiv:1911.05642v3
fatcat:k55v2icilnblpcunxougmfjw54
An Exploratory Analysis on Users' Contributions in Federated Learning
2020
2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)
Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition. ...
Its core principle is to learn from large amount of users data while preserving data privacy by design as collaborative users only need to share the machine learning models and keep data locally. ...
Thus, contract theory is a type of Unbalanced Stackelberg game, with the federator as the leader and dominant the optimization objective of the federated learning system. ...
doi:10.1109/tps-isa50397.2020.00014
fatcat:ey4zo4htwfcybg5euc2axtkqtq
An Exploratory Analysis on Users' Contributions in Federated Learning
[article]
2020
arXiv
pre-print
Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition. ...
Its core principle is to learn from large amount of users data while preserving data privacy by design as collaborative users only need to share the machine learning models and keep data locally. ...
Thus, contract theory is a type of Unbalanced Stackelberg game, with the federator as the leader and dominant the optimization objective of the federated learning system. ...
arXiv:2011.06830v1
fatcat:hn5utzq2nvh5tlmmroiw6wqb7y
Federated Ecology: Steps Toward Confederated Intelligence
2021
IEEE Transactions on Computational Social Systems
Federated ecology involves many fields such as machine learning algorithms, distributed machine learning, cryptography and security, privacy-preserving data mining, game theory, and so on. ...
They propose a long-term memory cell on actions and game context to learn the hidden representations. ...
doi:10.1109/tcss.2021.3063801
fatcat:6ya7ghhqircjbmm4ihc5i34vwm
Stackelberg Security Game For Optimizing Security Of Federated Internet Of Things Platform Instances
2017
Zenodo
This paper presents an approach for optimal cyber security decisions to protect instances of a federated Internet of Things (IoT) platform in the cloud. ...
We augment the repeated SSG (including SHARP and SUQR) with a reinforced learning algorithm called Naïve Q-Learning. ...
Such a game is formulated as a Stackelberg Game and uses linear programming to solve the identified problem. ...
doi:10.5281/zenodo.1130143
fatcat:ioupac6cbvaz3lftjcptnz5aru
Social-Aware Clustered Federated Learning with Customized Privacy Preservation
[article]
2024
arXiv
pre-print
Considering users' heterogeneous training samples and data distributions, we formulate the optimal social cluster formation problem as a federation game and devise a fair revenue allocation mechanism to ...
Experiments on Facebook network and MNIST/CIFAR-10 datasets validate that our SCFL can effectively enhance learning utility, improve user payoff, and enforce customizable privacy protection. ...
Federation Game Formulation In federation game, the mutual communication capability among all players is a basic assumption, which the social network in our work can enable. ...
arXiv:2212.13992v2
fatcat:zitdkyg63vhknpacrjvpnh3h6y
Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
[article]
2019
arXiv
pre-print
To strengthen data privacy and security, federated learning as an emerging machine learning technique is proposed to enable large-scale nodes, e.g., mobile devices, to distributedly train and globally ...
in federated learning. ...
Computation Model for Federated Learning We consider a federated learning task as a monopoly market with a monopolist operator (a task publisher) and a set of mobile devices N = {1, . . . , N }. ...
arXiv:1905.07479v2
fatcat:jhyv7ks4gfes5i4ngdpb6f22uy
FedParking: A Federated Learning based Parking Space Estimation with Parked Vehicle assisted Edge Computing
2021
IEEE Transactions on Vehicular Technology
As a distributed learning approach, federated learning trains a shared learning model over distributed datasets while preserving the training data privacy. ...
We formulate the interactions among the PLOs and vehicles as a multi-lead multi-follower Stackelberg game. ...
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
Exploring the Potential Impact of Serious Games on Social Learning and Stakeholder Collaborations for Transboundary Watershed Management of the St. Lawrence River Basin
2016
Water
The meaningful participation of stakeholders in decision-making is now widely recognized as a crucial element of effective water resource management, particularly with regards to adapting to climate and ...
Social learning has been identified as particularly important in transboundary contexts, where it is necessary to reframe problems from a local to a basin-wide perspective. ...
Serious games may therefore be seen as a form of intervention within a multi-stakeholder network setting that involves learning and changing of stakeholders' mental frames of transboundary water issues ...
doi:10.3390/w8050175
fatcat:xurmli5dfnaklbx24dinqjyduq
Achieving Lightweight Federated Advertising with Self-Supervised Split Distillation
[article]
2022
arXiv
pre-print
As an emerging secure learning paradigm in leveraging cross-agency private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary ...
Empirical studies on three industrial datasets exhibit the effectiveness of our methods, with the median AUC over all datasets improved by 0.86% and 2.6% in the local deployment mode and the federated ...
We use α as a hyper-parameter to balance the effect of raw label and the federated soft label. ...
arXiv:2205.15987v3
fatcat:hknahx6qffeinjm7lwiblvvc4e
Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective
[article]
2021
arXiv
pre-print
Federated learning (FL) becomes popular and has shown great potentials in training large-scale machine learning (ML) models without exposing the owners' raw data. ...
In this paper, we provide a comprehensive review for the economic and game theoretic approaches proposed in the literature to design various schemes for stimulating data owners to participate in FL training ...
INCENTIVE MECHANISM DESIGN FOR FEDERATED LEARNING
A. ...
arXiv:2111.11850v1
fatcat:24xqnqiqtbh2hdn6lnkdkctqii
Special Issue on Artificial-Intelligence-Powered Edge Computing for Internet of Things
2020
IEEE Internet of Things Journal
In the article "Hierarchical incentive mechanism design for federated machine learning in mobile networks," Lim et al. proposed a federated learning-based privacypreserving approach to facilitate collaborative ...
and energy efficiency, as well as to mitigate the network traffic burdens. ...
doi:10.1109/jiot.2020.3019948
fatcat:mogalqnhnnaqpbxb7zivzdhvry
Scalable Multi-agent Reinforcement Learning Algorithm for Wireless Networks
[article]
2021
arXiv
pre-print
Our result shows that the learning structure can effectively solve the cooperation problem in a large scale network with decent scalability. ...
Reinforcement learning (RL) is known as model-free and high efficient intelligent algorithm for communication problems and proved useful in the communication network. ...
We highlighted that federated learning can effectively accelerate the convergence speed and enhance cooperation. We investigated the theoretical basis for the benefit of federated learning. ...
arXiv:2108.00506v3
fatcat:7f7lu25bjvc3jjjiviutdws2am
A Comprehensive Survey On Client Selections in Federated Learning
[article]
2023
arXiv
pre-print
Federated Learning (FL) is a rapidly growing field in machine learning that allows data to be trained across multiple decentralized devices. ...
We also cover performance-aware selections and as well as resource-aware selections for resource-constrained networks and heterogeneous networks. ...
The authors in [40] propose a novel approach to developing an incentive mechanism for Federated Learning (FL) using game theory by using the framework of a Stackelberg game in which FL users are the ...
arXiv:2311.06801v1
fatcat:z6w3wzegvza3posfhjvs4fhfui
« Previous
Showing results 1 — 15 out of 83,618 results