Research Area:  Machine Learning

Abstract:

Many IoT applications at the network edge demand intelligent decisions in a real-time manner. The edge device alone, however, often cannot achieve real-time edge intelligence due to its constrained computing resources and limited local data. To tackle these challenges, we propose a platform-aided collaborative learning framework where a model is first trained across a set of source edge nodes by a federated meta-learning approach, and then it is rapidly adapted to learn a new task at the target edge node, using a few samples only. Further, we investigate the convergence of the proposed federated meta-learning algorithm under mild conditions on node similarity and the adaptation performance at the target edge. To combat against the vulnerability of meta-learning algorithms to possible adversarial attacks, we further propose a robust version of the federated meta-learning algorithm based on distributionally robust optimization, and establish its convergence under mild conditions. Experiments on different datasets demonstrate the effectiveness of the proposed Federated Meta-Learning based framework.

Keywords:  
Adaptation models
Collaborative work
Real-time systems
Internet of Things
Task analysis
Optimization
Convergence

Author(s) Name:  Sen Lin; Guang Yang; Junshan Zhang

Publisher name:  IEEE

DOI:  10.1109/ICDCS47774.2020.00032

Volume Information:  

Paper Link:   https://ieeexplore.ieee.org/abstract/document/9355664