FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912880136290304 |
|---|---|
| author | Commey, Daniel Abbad, Kamel Crosby, Garth V. Khoukhi, Lyes |
| author_facet | Commey, Daniel Abbad, Kamel Crosby, Garth V. Khoukhi, Lyes |
| contents | Communication overhead remains a primary bottleneck in federated learning (FL), particularly for applications involving mobile and IoT devices with constrained bandwidth. This work introduces FedSkipTwin, a novel client-skipping algorithm driven by lightweight, server-side digital twins. Each twin, implemented as a simple LSTM, observes a client's historical sequence of gradient norms to forecast both the magnitude and the epistemic uncertainty of its next update. The server leverages these predictions, requesting communication only when either value exceeds a predefined threshold; otherwise, it instructs the client to skip the round, thereby saving bandwidth. Experiments are conducted on the UCI-HAR and MNIST datasets with 10 clients under a non-IID data distribution. The results demonstrate that FedSkipTwin reduces total communication by 12-15.5% across 20 rounds while simultaneously improving final model accuracy by up to 0.5 percentage points compared to the standard FedAvg algorithm. These findings establish that prediction-guided skipping is a practical and effective strategy for resource-aware FL in bandwidth-constrained edge environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13624 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning Commey, Daniel Abbad, Kamel Crosby, Garth V. Khoukhi, Lyes Machine Learning Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Communication overhead remains a primary bottleneck in federated learning (FL), particularly for applications involving mobile and IoT devices with constrained bandwidth. This work introduces FedSkipTwin, a novel client-skipping algorithm driven by lightweight, server-side digital twins. Each twin, implemented as a simple LSTM, observes a client's historical sequence of gradient norms to forecast both the magnitude and the epistemic uncertainty of its next update. The server leverages these predictions, requesting communication only when either value exceeds a predefined threshold; otherwise, it instructs the client to skip the round, thereby saving bandwidth. Experiments are conducted on the UCI-HAR and MNIST datasets with 10 clients under a non-IID data distribution. The results demonstrate that FedSkipTwin reduces total communication by 12-15.5% across 20 rounds while simultaneously improving final model accuracy by up to 0.5 percentage points compared to the standard FedAvg algorithm. These findings establish that prediction-guided skipping is a practical and effective strategy for resource-aware FL in bandwidth-constrained edge environments. |
| title | FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Networking and Internet Architecture |
| url | https://arxiv.org/abs/2507.13624 |