A Collaborative Learning Framework via Federated Meta-Learning

By Sen Lin, Guang Yang, Junshan Zhang. 2020

95 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Robust Aggregation for Federated Learning (2019, background): “Recent work has looked beyond supervised learning to domains such as data analytics but also semi-, self- and un-supervised learning, transfer learning, meta learning, and reinforcement learning [46, 58, 76, 91].”
FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring (2020, background): “, slow convergence rate, degraded accuracy and overfitting with a few data samples) [18].”
Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, methodology): “To combat the possible vulnerabilities of meta-learning algorithms, a federated meta-learning method named FedML [132] is established based on distribution robust optimization (DRO).”
Federated Learning with Compression: Unified Analysis and Sharp Guarantees (2020, background): “Also, the personalization of local models for a better generalization in a heterogeneous setting is of great importance from both theoretical and practical point of view [7,8, 27,32,43].”
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach (2020, background): “In addition, an independent and concurrent work [35] studies a similar formulation theoretically for the case of strongly convex functions.”
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift (2020, methodology): “Also of particular interest are methods for robustness or adaptation to different users [29, 10, 34, 48, 38, 17, 40], a setting commonly referred to as robust or fair federated learning [45, 48, 38].”