Guiding Federated Learning with Inferenced Formal Logic Properties
Guiding Federated Learning with Inferenced Formal Logic Properties
复制标题
DOI：
10.1145/3576841.3589633
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Ziyan An;Meiyi Ma
中科院分区：
文献类型：
--
作者：
Ziyan An;Meiyi Ma
联邦学习 (FL) 的最新进展促进了去中心化协作物联网 (IoT) 应用程序的开发。然而，数据驱动的 FL 算法面临着参与物联网设备异构性的挑战，包括其部署环境和校准设置。不遵循这些特定于设备的属性可能会降低模型性能。为了解决这个问题，我们在这篇海报摘要中介绍了 FedSTL，它是一个两阶段的个性化 FL 框架，具有用于物联网中顺序预测任务的集群。 FedSTL 首先将客户端属性识别为信号时态逻辑 (STL) 规范。然后，FedSTL 的分区组件将每个客户端关联到聚合中心，同时框架继续推断集群的属性。在训练阶段，鼓励集群和客户端模型遵循定制属性，以实现分层属性增强策略。此外，我们在这篇海报摘要中展示了 FedSTL 在合成多任务 IoT 环境和现实世界流量预测场景下的初步结果。
Recent progressions in federated learning (FL) have facilitated the development of decentralized collaborative Internet-of-Things (IoT) applications. However, data-driven FL algorithms face the challenge of heterogeneity in participating IoT devices, including their deployment environment and calibration settings. Fail to follow these device-specific properties can degenerate the model performance. To address this issue, we present FedSTL in this poster abstract, which is a two-staged personalized FL framework with clustering for sequential prediction tasks in IoT. FedSTL first identifies client properties as Signal Temporal Logic (STL) specifications. Then, a partitioning component of FedSTL associates each client to an aggregation center, while the framework continues to infer properties for the cluster. At the training stage, both cluster and client models are encouraged to follow customized properties to achieve a hierarchical property enhancing strategy. Further, we show preliminary results of FedSTL in this poster abstract under a synthetic multitask IoT environment and a real-world traffic prediction scenario.