Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup

:::info
Authors:
(1) Halil Yigit Oksuz, Control Systems Group at Technische Universitat Berlin, Germany and Exzellenzcluster Science of Intelligence, Technische Universitat Berlin, Marchstr. 23, 10587, Berlin, Germany;
(2) Fabio Molinari, Control Syste…


This content originally appeared on HackerNoon and was authored by Computational Technology for All

:::info Authors:

(1) Halil Yigit Oksuz, Control Systems Group at Technische Universitat Berlin, Germany and Exzellenzcluster Science of Intelligence, Technische Universitat Berlin, Marchstr. 23, 10587, Berlin, Germany;

(2) Fabio Molinari, Control Systems Group at Technische Universitat Berlin, Germany;

(3) Henning Sprekeler, Exzellenzcluster Science of Intelligence, Technische Universit¨at Berlin, Marchstr. 23, 10587, Berlin, Germany and Modelling Cognitive Processes Group at Technische Universit¨at Berlin, Germany;

(4) Jorg Raisch, Control Systems Group at Technische Universitat Berlin, Germany and Exzellenzcluster Science of Intelligence, Technische Universitat Berlin, Marchstr. 23, 10587, Berlin, Germany.

:::

Abstract and Introduction

Problem Setup

Federated fair over-the-air learning (FedAir) Algorithm

Convergence Properties

Numerical Example

Conclusion and References

II. PROBLEM SETUP

\ A. Minmax Reformulation

\ In a federated learning setting with N agents, where V = {1,2,··· ,N} denotes the index set, we are interested in improving the performance of the worst-performing agent by solving the following optimization problem:

\

\ We aim to compute a parameter vector estimate minimizing the worst-case loss observed among all agents, thus providing some form of fairness [20], [21]. However, it is difficult and inefficient to use (3) directly for federated learning purposes. Instead, we can consider an alternative (epigraph) form:

\

\ B. Over-the-Air Communication Mode

\

\

:::info This paper is available on arxiv under CC BY 4.0 DEED license.

:::

\


This content originally appeared on HackerNoon and was authored by Computational Technology for All


Print Share Comment Cite Upload Translate Updates
APA

Computational Technology for All | Sciencx (2024-10-27T19:46:41+00:00) Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup. Retrieved from https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/

MLA
" » Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup." Computational Technology for All | Sciencx - Sunday October 27, 2024, https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/
HARVARD
Computational Technology for All | Sciencx Sunday October 27, 2024 » Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup., viewed ,<https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/>
VANCOUVER
Computational Technology for All | Sciencx - » Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/
CHICAGO
" » Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup." Computational Technology for All | Sciencx - Accessed . https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/
IEEE
" » Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup." Computational Technology for All | Sciencx [Online]. Available: https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/. [Accessed: ]
rf:citation
» Boosting Fairness and Robustness in Over-the-Air Federated Learning: Problem Setup | Computational Technology for All | Sciencx | https://www.scien.cx/2024/10/27/boosting-fairness-and-robustness-in-over-the-air-federated-learning-problem-setup/ |

Please log in to upload a file.



There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

Related Posts