A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914555208138752 |
|---|---|
| author | Makris, Antonios Dousis, Christos Kritharakis, Emmanouil Bouras, Stavros Tserpes, Konstantinos |
| author_facet | Makris, Antonios Dousis, Christos Kritharakis, Emmanouil Bouras, Stavros Tserpes, Konstantinos |
| contents | Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates at the server, which directly affects learning performance, robustness, and system behavior. This work presents a comprehensive experimental comparison of widely used federated aggregation strategies under both homogeneous and heterogeneous data distributions. Using benchmark image classification datasets, we analyze how different aggregation mechanisms respond to varying degrees of data heterogeneity, examining their impact on centralized accuracy and loss, and system-level efficiency metrics, including aggregation, training, and communication time. The results demonstrate that aggregation strategies exhibit distinct trade-offs across datasets and data distributions, with their effectiveness varying according to dataset characteristics and operating conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11010 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions Makris, Antonios Dousis, Christos Kritharakis, Emmanouil Bouras, Stavros Tserpes, Konstantinos Machine Learning Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates at the server, which directly affects learning performance, robustness, and system behavior. This work presents a comprehensive experimental comparison of widely used federated aggregation strategies under both homogeneous and heterogeneous data distributions. Using benchmark image classification datasets, we analyze how different aggregation mechanisms respond to varying degrees of data heterogeneity, examining their impact on centralized accuracy and loss, and system-level efficiency metrics, including aggregation, training, and communication time. The results demonstrate that aggregation strategies exhibit distinct trade-offs across datasets and data distributions, with their effectiveness varying according to dataset characteristics and operating conditions. |
| title | A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.11010 |