Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.12762 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908711472070656 |
|---|---|
| author | Baek, Incheol Kim, Hyungbin Kim, Minseo Chung, Yon Dohn |
| author_facet | Baek, Incheol Kim, Hyungbin Kim, Minseo Chung, Yon Dohn |
| contents | Federated Learning (FL) enables collaborative training across multiple clients while preserving data privacy, yet it struggles with data heterogeneity, where clients' data are not distributed independently and identically (non-IID). This causes local drift, hindering global model convergence. To address this, we introduce Federated Learning with Feedback Alignment (FLFA), a novel framework that integrates feedback alignment into FL. FLFA uses the global model's weights as a shared feedback matrix during local training's backward pass, aligning local updates with the global model efficiently. This approach mitigates local drift with minimal additional computational cost and no extra communication overhead.
Our theoretical analysis supports FLFA's design by showing how it alleviates local drift and demonstrates robust convergence for both local and global models. Empirical evaluations, including accuracy comparisons and measurements of local drift, further illustrate that FLFA can enhance other FL methods demonstrating its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12762 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Learning with Feedback Alignment Baek, Incheol Kim, Hyungbin Kim, Minseo Chung, Yon Dohn Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Federated Learning (FL) enables collaborative training across multiple clients while preserving data privacy, yet it struggles with data heterogeneity, where clients' data are not distributed independently and identically (non-IID). This causes local drift, hindering global model convergence. To address this, we introduce Federated Learning with Feedback Alignment (FLFA), a novel framework that integrates feedback alignment into FL. FLFA uses the global model's weights as a shared feedback matrix during local training's backward pass, aligning local updates with the global model efficiently. This approach mitigates local drift with minimal additional computational cost and no extra communication overhead. Our theoretical analysis supports FLFA's design by showing how it alleviates local drift and demonstrates robust convergence for both local and global models. Empirical evaluations, including accuracy comparisons and measurements of local drift, further illustrate that FLFA can enhance other FL methods demonstrating its effectiveness. |
| title | Federated Learning with Feedback Alignment |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.12762 |