Sharing of telecommunication network data, for example, even at high aggregation levels, is nowadays highly restricted due to privacy legislation and regulations and other important ethical concerns. It leads to scattering data across institutions, regions, and states, inhibiting the usage of AI methods that could otherwise take advantage of data at scale. It creates the need to build a platform to control such data, build models or perform calculations. In this work, we propose an approach to building the bridge among anomaly detection, federated learning, and data streams. The overarching goal of the work is to detect anomalies in a federated environment over distributed data streams. This work complements the state-of-the-art by adapting the data stream algorithms in a federated learning setting for anomaly detection and by delivering a robust framework and demonstrating the practical feasibility in a real-world distributed deployment scenario.
翻译:例如,共享电信网络数据,即使是在高汇总水平上,如今由于隐私法规和其他重要的伦理问题,共享电信网络数据也受到严重限制,导致数据分散在各机构、区域和州之间,抑制使用非利用大规模数据可使用的AI方法,从而需要建立一个平台来控制这些数据、建立模型或进行计算。在这项工作中,我们提议了在异常现象检测、联合学习和数据流之间搭建桥梁的方法。工作的首要目标是在分布式数据流的联结环境中发现异常现象。这项工作补充了最新数据流算法,将数据流算法改编成一个用于发现异常现象的联结学习环境,并提供一个强有力的框架,在实际分布式部署情景中展示实际可行性。