# Contextual Model Aggregation for Fast and Robust Federated Learning in Edge Computing

@article{Nguyen2022ContextualMA,
title={Contextual Model Aggregation for Fast and Robust Federated Learning in Edge Computing},
author={Hung T. Nguyen and H. Vincent Poor and Mung Chiang},
journal={ArXiv},
year={2022},
volume={abs/2203.12738}
}
• Published 23 March 2022
• Computer Science
• ArXiv
Federated learning is a prime candidate for distributed machine learning at the network edge due to the low communication complexity and privacy protection among other attractive properties. However, existing algorithms face issues with slow convergence and/or robustness of performance due to the considerable heterogeneity of data distribution, computation and communication capability at the edge. In this work, we tackle both of these issues by focusing on the key component of model aggregation…

## References

SHOWING 1-10 OF 33 REFERENCES

• Computer Science
IEEE Journal on Selected Areas in Communications
• 2019
This paper analyzes the convergence bound of distributed gradient descent from a theoretical point of view, and proposes a control algorithm that determines the best tradeoff between local update and global parameter aggregation to minimize the loss function under a given resource budget.
• Computer Science
ArXiv
• 2021
An adaptive control algorithm is developed that tunes the step size, D2D communication rounds, and global aggregation period of TT-HF over time to target a sublinear convergence rate of O(1/t) while minimizing network resource utilization.
• Computer Science
IEEE Journal on Selected Areas in Communications
• 2021
A fast-convergent federated learning algorithm, called <inline-formula>, which performs intelligent sampling of devices in each round of model training to optimize the expected convergence speed and experimentally show its improvement in trained model accuracy, convergence speed, and/or model stability across various machine learning tasks and datasets.
• Computer Science
IEEE INFOCOM 2021 - IEEE Conference on Computer Communications
• 2021
A sampling methodology based on graph convolutional networks (GCNs) which learns the relationship between network attributes, sampled nodes, and resulting offloading that maximizes FedL accuracy is developed.
• Computer Science
MLSys
• 2020
This work introduces a framework, FedProx, to tackle heterogeneity in federated networks, and provides convergence guarantees for this framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work.
• Computer Science
NeurIPS
• 2020
This work proposes an algorithm for personalized FL (pFedMe) using Moreau envelopes as clients' regularized loss functions, which help decouple personalized model optimization from the global model learning in a bi-level problem stylized for personalizedFL.
• Computer Science
ICLR
• 2020
This paper analyzes the convergence of Federated Averaging on non-iid data and establishes a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.
• Computer Science
IEEE INFOCOM 2020 - IEEE Conference on Computer Communications
• 2020
This work analytically characterize the optimal data transfer solution for different fog network topologies, showing for example that the value of a device offloading is approximately linear in the range of computing costs in the network.
• Computer Science
ICML
• 2020
This work obtains tight convergence rates for FedAvg and proves that it suffers from client-drift' when the data is heterogeneous (non-iid), resulting in unstable and slow convergence, and proposes a new algorithm (SCAFFOLD) which uses control variates (variance reduction) to correct for the  client-drifts' in its local updates.
• Computer Science
AISTATS
• 2017
This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.