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
Federated Reconstruction: Partially Local Federated Learning
[article]
2022
arXiv
pre-print
We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. ...
Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. ...
Other federated learning works have also established connections to meta learning: Jiang et al. ...
arXiv:2102.03448v6
fatcat:shjujqe6rjcbvkrsovfo7ktm3u
Learning to Backdoor Federated Learning
[article]
2023
arXiv
pre-print
In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. ...
In particular, we propose a general reinforcement learning-based backdoor attack framework where the attacker first trains a (non-myopic) attack policy using a simulator built upon its local data and common ...
Federated Learning Setting. ...
arXiv:2303.03320v1
fatcat:wobwl5n5cjaypfuosq47lf2b6q
Coded Federated Learning
[article]
2020
arXiv
pre-print
Federated learning is a method of training a global model from decentralized data distributed across client devices. ...
This paper develops a novel coded computing technique for federated learning to mitigate the impact of stragglers. ...
Section II outlines federated learning method for linear regression model. Section III describes the coded federated learning algorithm. ...
arXiv:2002.09574v1
fatcat:hg4f5iwijjfhdeapc3t52jtnpy
Dynamic Federated Learning
[article]
2020
arXiv
pre-print
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. ...
We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. ...
TABLE I : I List of references on the convergence analysis of federated learning under different assumptions. This work is the
only one to tackle the 3 challenges of federated learning. ...
arXiv:2002.08782v2
fatcat:l5cvo2kynnf55lbbetrjsc7bxq
Modular Federated Learning
[article]
2022
arXiv
pre-print
This paper proposes ModFL as a federated learning framework that splits the models into a configuration module and an operation module enabling federated learning of the individual modules. ...
Federated learning is an approach to train machine learning models on the edge of the networks, as close as possible where the data is produced, motivated by the emerging problem of the inability to stream ...
We call this concept modular federated learning ModFL. ...
arXiv:2209.03090v1
fatcat:hbxqazas55hqti6umtzzabzf44
Active Federated Learning
[article]
2019
arXiv
pre-print
Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients ...
To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client ...
Figure 1 : 1 Active Federated Learning framework for a binary classification problem. ...
arXiv:1909.12641v1
fatcat:rybnm46hs5d7zmprnv2gi3zfui
Federated Mutual Learning
[article]
2020
arXiv
pre-print
Federated learning (FL) enables collaboratively training deep learning models on decentralized data. ...
learning paradigm, named Federated Mutual Leaning (FML), dealing with the three heterogeneities. ...
These three datasets are widely used in federated learning. Federated settings We configure our experiments with a simulated cross-silo federated learning environment. ...
arXiv:2006.16765v3
fatcat:3kifsth6kng4zntkc3krp5sv7a
Anarchic Federated Learning
[article]
2022
arXiv
pre-print
To satisfy the need for flexible worker participation, we consider a new FL paradigm called "Anarchic Federated Learning" (AFL) in this paper. ...
Present-day federated learning (FL) systems deployed over edge networks consists of a large number of workers with high degrees of heterogeneity in data and/or computing capabilities, which call for flexible ...
Introduction Federated Learning (FL) has recently emerged as an important distributed learning framework that leverages numerous workers to collaboratively learn a joint model (Li et al., 2019a; Yang ...
arXiv:2108.09875v4
fatcat:7zmcpl5qvfdjjcovoyi52uirku
Incentivizing Federated Learning
[article]
2022
arXiv
pre-print
Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. ...
The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local data. ...
Fairness in Federated Learning Fairness for federated learning is another close topic to our research. ...
arXiv:2205.10951v1
fatcat:eowmag2ap5f3vdqeyahzpqhfci
Federated Residual Learning
[article]
2020
arXiv
pre-print
We study a new form of federated learning where the clients train personalized local models and make predictions jointly with the server-side shared model. ...
Our framework is robust to data heterogeneity, addressing the slow convergence problem traditional federated learning methods face when the data is non-i.i.d. across clients. ...
Related work Federated learning has become a popular topic in machine learning. ...
arXiv:2003.12880v1
fatcat:omtz7hchhvg6haepck3r4o5juq
Semi-Federated Learning
[article]
2020
arXiv
pre-print
Federated learning (FL) enables massive distributed Information and Communication Technology (ICT) devices to learn a global consensus model without any participants revealing their own data to the central ...
In this work, we propose the Semi-Federated Learning (Semi-FL) which differs from the FL in two aspects, local clients clustering and in-cluster training. ...
In this work, we firstly proposed the Semi-Federated Learning architecture which extends the federated learning. ...
arXiv:2003.12795v1
fatcat:2ejdzx7zp5bnjl2aukemxdf3t4
Agnostic Federated Learning
[article]
2019
arXiv
pre-print
A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. ...
We present data-dependent Rademacher complexity guarantees for learning with this objective, which guide the definition of an algorithm for agnostic federated learning. ...
Motivation A key learning scenario in large-scale applications is that of federated learning. ...
arXiv:1902.00146v1
fatcat:5uv3gbio65boddwuanm2ryh57q
Meta Federated Learning
[article]
2021
arXiv
pre-print
To this end, we propose Meta Federated Learning (Meta-FL), a novel variant of federated learning which not only is compatible with secure aggregation protocol but also facilitates defense against backdoor ...
Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. ...
META FEDERATED LEARNING In this section, we first discuss the challenges in mitigating backdoor attacks in federated learning. ...
arXiv:2102.05561v1
fatcat:2ri6iry5prg3fbojkwa2zh3p6u
Networked Federated Learning
[article]
2022
arXiv
pre-print
This formulation unifies and considerably extends existing federated multi-task learning methods. ...
Our main conceptual contribution is to formulate networked federated learning using a generalized total variation minimization. ...
Federated learning (FL) is an umbrella term for machine learning (ML) techniques that collaboratively train models on decentralized collections of local datasets [7] - [9] . ...
arXiv:2105.12769v3
fatcat:m665ijngnndvxgb5xmytpmsgeq
Heterogeneous Federated Learning
[article]
2022
arXiv
pre-print
Federated learning learns from scattered data by fusing collaborative models from local nodes. ...
In this work, we propose a novel federated learning framework to resolve this issue by establishing a firm structure-information alignment across collaborative models. ...
Introduction Federated Learning (FL) has drawn great attention with outstanding collaborative training performance and data privacy supportability [6] . ...
arXiv:2008.06767v2
fatcat:puw4zdefivefjcp5nszyybrt7q
« Previous
Showing results 1 — 15 out of 803,103 results