Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning
This work addresses the problem of real-time intelligent decision-making for IoT applications at the network edge, offering a solution that is incremental by combining federated learning and meta-learning.
The paper tackles the challenge of achieving real-time edge intelligence for IoT applications by proposing a collaborative learning framework that uses federated meta-learning to train models across source nodes and rapidly adapt them to new tasks at target nodes with few samples, demonstrating effectiveness through experiments on various datasets.
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.