CREWS: Collaborative Robust Edge WiFi Sensing with Asynchronous and Incomplete Observations
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_ | 1866917544856649728 |
|---|---|
| author | Chen, Yinan Zhou, Yang Huang, Xiaoxia Li, Pan |
| author_facet | Chen, Yinan Zhou, Yang Huang, Xiaoxia Li, Pan |
| contents | Existing collaborative WiFi sensing systems rely on perfect node synchronization and complete data availability. However, real-world edge deployments suffer from heterogeneous computing and network dropouts, leading to asynchronous and incomplete features. We propose CREWS, a robust collaborative sensing framework that inherently resists these network volatility. First, CREWS employs a topology-agnostic aggregator invariant to the arrival order and subset size of incoming features. Second, rather than discarding delayed observations, it utilizes a staleness-aware adaptive replay mechanism. By treating stale features from lagging nodes as system-induced hard samples, CREWS transforms synchronization delays into beneficial training regularization. We theoretically prove the joint convergence of this architecture and demonstrate how replay bounds the bias-variance trade-off. Extensive evaluations and an 8-node heterogeneous hardware testbed demonstrate its superior resilience. Under severe conditions i.e., 50\% transient dropout rate or out-of-distribution jitter, CREWS restricts accuracy degradation to merely 2.2 percentage points, substantially outperforming state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30356 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CREWS: Collaborative Robust Edge WiFi Sensing with Asynchronous and Incomplete Observations Chen, Yinan Zhou, Yang Huang, Xiaoxia Li, Pan Networking and Internet Architecture Existing collaborative WiFi sensing systems rely on perfect node synchronization and complete data availability. However, real-world edge deployments suffer from heterogeneous computing and network dropouts, leading to asynchronous and incomplete features. We propose CREWS, a robust collaborative sensing framework that inherently resists these network volatility. First, CREWS employs a topology-agnostic aggregator invariant to the arrival order and subset size of incoming features. Second, rather than discarding delayed observations, it utilizes a staleness-aware adaptive replay mechanism. By treating stale features from lagging nodes as system-induced hard samples, CREWS transforms synchronization delays into beneficial training regularization. We theoretically prove the joint convergence of this architecture and demonstrate how replay bounds the bias-variance trade-off. Extensive evaluations and an 8-node heterogeneous hardware testbed demonstrate its superior resilience. Under severe conditions i.e., 50\% transient dropout rate or out-of-distribution jitter, CREWS restricts accuracy degradation to merely 2.2 percentage points, substantially outperforming state-of-the-art baselines. |
| title | CREWS: Collaborative Robust Edge WiFi Sensing with Asynchronous and Incomplete Observations |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2605.30356 |