A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Models of fairness in federated learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
Other Versions
Federated learning is a novel distributed learning approach that allows multiple federating agents to jointly learn a model. ...
In this work, we consider two notions of fairness that each may be appropriate in different circumstances: egalitarian fairness (which aims to bound how dissimilar error rates can be) and proportional ...
Acknowledgments This work was supported in part by a Simons Investigator Award, a Vannevar Bush Faculty Fellowship, MURI grant W911NF-19-0217, AFOSR grant FA9550-19-1-0183, ARO grant W911NF19-1-0057, a ...
arXiv:2112.00818v2
fatcat:xminw57renff5nfuvzo74kzfam
Fair and autonomous sharing of federate learning models in mobile Internet of Things
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2007.10650v1 fatcat:wmbsamm4bjgmlpdxhfdj4to76u
Federate learning can conduct machine learning as well as protect the privacy of self-owned training data on corresponding ends, instead of having to upload to a central trusted data aggregation server ...
The proposed protocol does not rely on a trusted third party, where individual-learned models are shared/stored in corresponding ends. ...
The Application of Blockchain in Federated Learning Federate learning can conduct machine learning as well as protect the privacy of self-owned training data on corresponding ends, instead of uploading ...
arXiv:2007.10650v2
fatcat:7dpdyhavjfdizn4iyouoqa3w4y
A Fair Federated Learning Framework With Reinforcement Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. ...
The experimental results show that our framework can outperform baseline methods in terms of overall performance, fairness and convergence speed. ...
For the federated model, we add the fairness indicator and use a plug-in based on the deep reinforcement learning (DRL) algorithm that can be used for any federated learning algorithm that does not involve ...
arXiv:2205.13415v1
fatcat:fu5y365t25br5jutyjd7xjlqcy
Blockchain-based Trustworthy Federated Learning Architecture
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture. ...
The proposed algorithm can achieve better performance than the default federated learning setting in terms of the model's generalisation and accuracy. ...
In this work, we focus on the accountability and fairness challenges of trustworthy federated learning. ...
arXiv:2108.06912v2
fatcat:y2qrpahwtjh3zjteqveduo3puq
Hierarchically Fair Federated Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Theoretical analysis and empirical evaluation on several datasets confirm the efficacy of our frameworks in upholding fairness and thus facilitating federated learning in the competitive settings. ...
We propose a novel hierarchically fair federated learning (HFFL) framework. Under this framework, agents are rewarded in proportion to their pre-negotiated contribution levels. ...
This necessitates the notion of fairness in federated learning. ...
arXiv:2004.10386v2
fatcat:drv4bzujmrfwhe2domyr23bvli
FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a fair vertical federated learning framework (FairVFL), which can improve the fairness of VFL models. ...
However, existing fair ML methods usually rely on the centralized storage of fairness-sensitive features to achieve model fairness, which are usually inapplicable in federated scenarios. ...
Next, we will introduce the federated model serving, fair model learning, and federated model training framework of FairVFL. ...
arXiv:2206.03200v1
fatcat:ox6doodd2vgkzgwxuc7nfpbbam
FedFair: Training Fair Models In Cross-Silo Federated Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Then, we use the fairness estimation to formulate a novel problem of training fair models in cross-silo federated learning. ...
As many powerful models are built by collaboration among multiple parties, each holding some sensitive data, it is natural to explore the feasibility of training fair models in cross-silo federated learning ...
Federated Fair Model Training Now we formulate the task of training fair models in cross-silo federated learning (federated fair model training for short). ...
arXiv:2109.05662v1
fatcat:pl6ku6x5a5dkndqy637zytlrqa
Fairness-aware Agnostic Federated Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we develop a fairness-aware agnostic federated learning framework (AgnosticFair) to deal with the challenge of unknown testing distribution. ...
To our best knowledge, this is the first work to achieve fairness in federated learning. ...
model L(w) loss function of federated learning model L(w, α) loss function of agnostic federated learning model l(f k (x k i ; w), y k i ) loss value of t k i in u k α coefficients of reweighing function ...
arXiv:2010.05057v1
fatcat:cr4zyopz6vbhflatdlt55opzdq
Federating for Learning Group Fair Models
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
We experimentally compare the proposed approach against other methods in terms of group fairness in various federated learning setups. ...
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. ...
The development of fair machine learning models in federated learning settings has been building upon the group fairness literature. ...
arXiv:2110.01999v2
fatcat:2dgdy5kvi5dbpm7tmhrekcwabi
Towards Fair Federated Learning with Zero-Shot Data Augmentation
[article]
2021
arXiv
pre-print
Preserved Fulltext
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.
In this work, we aim to provide federated learning schemes with improved fairness. ...
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. ...
In addition, if the global model is fair, and each client updates the global model from the same fair initialization, federated learning can convergence faster to a fair solution. ...
arXiv:2104.13417v1
fatcat:ycavxam7kne3vmj7cmijglx25i
Towards Multi-Objective Statistically Fair Federated Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Federated Learning (FL) has emerged as a result of data ownership and privacy concerns to prevent data from being shared between multiple parties included in a training procedure. ...
With this goal in mind, we conduct studies to show that FL is able to satisfy different fairness metrics under different data regimes consisting of different types of clients. ...
learning (Truong et al. 2020) , personalization and federated learning (Fallah, Mokhtari, and Ozdaglar 2020) , and more recently work has been done in the context of fairness and federated learning ...
arXiv:2201.09917v1
fatcat:lf7nsg7jpzdavmh7xgwmngpsna
A Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices
2022
Future Internet
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Moreover, most weight averaging-based model aggregation schemes raise learning fairness concerns. In this paper, we propose a peer-to-peer decentralized learning framework to tackle the above issues. ...
Distributed machine learning paradigms have benefited from the concurrent advancement of deep learning and the Internet of Things (IoT), among which federated learning is one of the most promising frameworks ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/fi14050138
fatcat:mwbh5x6bkngmzjzjs7fnvxujwm
Fair Federated Learning via Bounded Group Loss
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work we propose a general framework for provably fair federated learning. ...
In federated learning, fair prediction across protected groups is an important constraint for many applications. ...
Further, we provide fairness and generalization guarantees on the model for a variety of fairness notions. • Finally, we evaluate our method on common benchmarks used in fair machine learning and federated ...
arXiv:2203.10190v2
fatcat:ixvdxqe36rao3alohpxgojikkm
Minimax Demographic Group Fairness in Federated Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. ...
We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or ...
The development of fair machine learning models in federated learning settings has been building upon the group fairness literature. ...
arXiv:2201.08304v2
fatcat:z6674ltxzfclrpzkmiamjnopze
Unified Group Fairness on Federated Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Federated learning (FL) has emerged as an important machine learning paradigm where a global model is trained based on the private data from distributed clients. ...
We validate the advantages of the FMDA-M algorithm with various kinds of distribution shift settings in experiments, and the results show that FMDA-M algorithm outperforms the existing fair FL algorithms ...
In this paper, we consider how to learn a fair global model that achieves a uniform performance across groups in FL. Federated Learning and Fairness. ...
arXiv:2111.04986v3
fatcat:4y2rv26vgvccfoex3oyvbu5mfe
« Previous
Showing results 1 — 15 out of 138,345 results