arXiv cs.AI· Mattia Giovanni Campana, Dariush Salami, H\"useyin Yi\u{g}itler, Stephan Sigg·· 12 小时前AI 评分22
PULSE：面向可穿戴设备的个性化机会学习框架
PULSE: Personalized Opportunistic Learning for Wearable Devices
AI 导读
PULSE 是一个事件驱动的个性化机会学习框架，将每次设备相遇视为在线协作决策，仅在邻近节点的梯度与本地学习方向兼容时才进行交互。在人类活动识别、跌倒检测和压力识别任务上，PULSE 保持或提升了个性化分类性能，同时相比机会式模型平均将节点间交换减少 80-94%。端侧实验显示其完整实现仅占用 149.8 KiB RAM 和 561.8 KiB flash，验证了在可穿戴硬件上的可行性。
正文 · 原文
Abstract:Wearable devices increasingly support personalized health and well-being applications, but post-deployment data can differ substantially from those used for training, while purely local adaptation may be limited by the data available on a single device during real-world operation. Conventional federated and decentralized learning rely on recurrent communication and stable connectivity, whereas existing opportunistic approaches often exploit available encounters without adequately considering their utility, compatibility, or communication cost.
We propose PULSE, an event-driven framework for personalized opportunistic learning that treats each encounter as an online collaboration decision, selecting either no interaction or a promising nearby peer. Peer gradients are incorporated only when compatible with the local learning direction, while past interactions guide future peer selection. Across human activity recognition, fall detection, and stress recognition under synthetic and real contact traces, PULSE preserves or improves personalized classification performance, while reducing peer-assisted exchanges by 80-94% compared with opportunistic model averaging. On-device experiments further demonstrate its feasibility on wearable hardware: peer-assisted operations require limited energy, while the complete implementation occupies 149.8 KiB of RAM and 561.8 KiB of flash. The obtained results show that selective opportunistic collaboration can provide effective personalization while limiting communication and resource demands on constrained wearable devices.
| Comments: | Submitted to IEEE PerCom 2027 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC) |
| Cite as: | arXiv:2610.28081 [cs.LG] |
| (or arXiv:2610.28081v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28081 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mattia Giovanni Campana [view email]
[v1]
Tue, 20 Oct 2026 12:00:38 UTC (703 KB)
来源：arXiv cs.AI · arxiv.org