Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring
Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring
复制标题
DOI：
--
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Gautham Krishna Gudur;S. K. Perepu
中科院分区：
文献类型：
--
作者：
Gautham Krishna Gudur;S. K. Perepu
各种医疗保健应用，如辅助生活、跌倒检测等，需要通过人类活动识别（HAR）对用户行为进行建模。这些应用需要使用机器学习技术来表征来自多个资源受限的用户设备的见解，以进行有效的个性化活动监控。设备上的联合学习被证明是分布式和协作机器学习的有效方法。然而，在解决用户之间的统计（非IID数据）和模型异质性方面存在各种挑战。此外，在本文中，我们探索了一个新的挑战-在联邦学习期间处理用户之间标签（活动）的异质性。为此，我们提出了一个框架，联邦标签为基础的聚合，利用重叠的信息增益跨活动使用模型蒸馏更新。我们还建议，模型分数的联邦传输是足够的，而不是从设备到服务器的模型权重传输。在Raspberry Pi 2上使用Heteroimmune Human Activity Recognition（HHAR）数据集（有四个活动用于有效阐明结果）进行的实证评估表明，平均确定性准确度至少提高了~ 11.01%，从而证明了我们提出的框架的设备上功能。
Various health-care applications such as assisted living, fall detection, etc., require modeling of user behavior through Human Activity Recognition (HAR). Such applications demand characterization of insights from multiple resource-constrained user devices using machine learning techniques for effective personalized activity monitoring. On-device Federated Learning proves to be an effective approach for distributed and collaborative machine learning. However, there are a variety of challenges in addressing statistical (non-IID data) and model heterogeneities across users. In addition, in this paper, we explore a new challenge of interest -- to handle heterogeneities in labels (activities) across users during federated learning. To this end, we propose a framework for federated label-based aggregation, which leverages overlapping information gain across activities using Model Distillation Update. We also propose that federated transfer of model scores is sufficient rather than model weight transfer from device to server. Empirical evaluation with the Heterogeneity Human Activity Recognition (HHAR) dataset (with four activities for effective elucidation of results) on Raspberry Pi 2 indicates an average deterministic accuracy increase of at least ~11.01%, thus demonstrating the on-device capabilities of our proposed framework.