ABSTRACT
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.
- Susmit Jha, Ashish Tiwari, Sanjit A Seshia, Tuhin Sahai, and Natarajan Shankar. 2017. Telex: Passive stl learning using only positive examples. In International Conference on Runtime Verification. Springer, 208--224.Google ScholarCross Ref
- MeiyiMa, Ji Gao, Lu Feng, and John Stankovic. 2020. STLnet: Signal temporal logic enforced multivariate recurrent neural networks. Advances in Neural Information Processing Systems 33 (2020), 14604--14614.Google Scholar
- Meiyi Ma, John Stankovic, Ezio Bartocci, and Lu Feng. 2021. Predictive monitoring with logic-calibrated uncertainty for cyber-physical systems. ACM Transactions on Embedded Computing Systems (TECS) 20, 5s (2021), 1--25.Google ScholarDigital Library
- Meiyi Ma, John A Stankovic, and Lu Feng. 2021. Toward formal methods for smart cities. Computer 54, 9 (2021), 39--48.Google ScholarDigital Library
- Oded Maler and Dejan Nickovic. 2004. Monitoring temporal properties of continuous signals. In Formal Techniques, Modelling and Analysis of Timed and Fault-Tolerant Systems. Springer, 152--166.Google Scholar
- Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR, 1273--1282.Google Scholar
Index Terms
- Guiding Federated Learning with Inferenced Formal Logic Properties
Recommendations
Federated Machine Learning: Concept and Applications
Survey Papers and Regular PapersToday’s artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these ...
On-device federated learning with fuzzy logic based client selection
RACS '22: Proceedings of the Conference on Research in Adaptive and Convergent SystemsWith the rapid development of IoT, more and more advanced sensor devices are used to collect and process a large number of datasets. In order to protect user privacy while training machine learning models with multiple datasets, federated learning (FL) ...
Resource optimizing federated learning for use with IoT: A systematic review
AbstractRecently, Federated Learning (FL) has been explored as a new paradigm that preserves both data privacy and end-users knowledge while reducing latency during model training. While often applied between a central server and the edge ...
Highlights- Federated Learning preserves data privacy and end-users knowledge.
- Federated ...
Comments