Artificial Intelligence of Thing
Artificial Intelligence of Things (AIoT) integrates artificial intelligence with the Internet of Things to create more autonomous and efficient systems across various sectors. Current research focuses on optimizing AIoT for resource-constrained environments, employing techniques like federated learning, knowledge distillation, and model pruning to improve energy efficiency and accuracy while preserving data privacy. This involves developing lightweight models, efficient training algorithms, and frameworks for managing heterogeneous devices and data distributions. The impact of AIoT extends to numerous applications, including smart homes, industrial automation, and supply chain management, driving advancements in both theoretical understanding and practical deployment of AI in resource-limited settings.
Papers
AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems
Chentao Jia, Ming Hu, Zekai Chen, Yanxin Yang, Xiaofei Xie, Yang Liu, Mingsong Chen
Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learning
Dengke Yan, Ming Hu, Zeke Xia, Yanxin Yang, Jun Xia, Xiaofei Xie, Mingsong Chen