TY  - CONF
T1  - Towards a Meaningful Communication and Model Aggregation in Federated Learning via Genetic Programming
A1  - Pacioni, Elia
A1  - Fernández de Vega, Francisco
A1  - Calvaresi, Davide
TI  - Proceedings of the 17th International Conference on Agents and Artificial Intelligence: ICAART
Y1  - 2025
VL  - 3
SP  - 1427
EP  - 1431
PB  - Springer
CY  - Porto, Portugal
SN  - 978-989-758-737-5
SN  - 2184-433X
UR  - https://www.scitepress.org/Papers/2025/133804/133804.pdf
M2  - doi: 10.5220/0013380400003890
KW  - Communication Efficiency
KW  - federated learning
KW  - Genetic Programming
KW  - Models Aggregation
KW  - Multi-Agent Systems
N2  - Federated Learning (FL) enables collaborative training of machine learning models while preserving client data privacy. However, its conventional client-server paradigm presents two key challenges: (i) communication efficiency and (ii) model aggregation optimization. Inefficient communication, often caused by transmitting low-impact updates, results in unnecessary overhead, particularly in bandwidth-constrained environments such as wireless or mobile networks or in scenarios with numerous clients. Furthermore, traditional aggregation strategies lack the adaptability required for stable convergence and optimal performance.
This paper emphasizes the distributed nature of FL clients (agents) and advocates for local, autonomous, and intelligent strategies to evaluate the significance of their updates—such as using a ''distance'' metric relative to the global model. This approach improves communication efficiency by prioritizing impactful updates. Additionally, the paper proposes an adaptive aggregation method leveraging genetic programming and transfer learning to dynamically evolve aggregation equations, optimizing the convergence process. By integrating insights from multi-agent systems, the proposed approach aims to foster more efficient and robust frameworks for decentralized learning.
ER  -