Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning

TL;DR

This paper introduces a federated meta-learning framework for real-time edge intelligence, enabling edge devices to quickly adapt to new tasks with limited data while ensuring robustness against adversarial attacks.

Contribution

It presents a novel federated meta-learning approach for edge devices, including convergence analysis and a robust version using distributionally robust optimization.

Findings

Effective adaptation to new tasks with few samples

Convergence guarantees under mild conditions

Enhanced robustness against adversarial attacks

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.