Optimizing Value of Learning in Task-Oriented Federated Meta-Learning Systems

TL;DR

This paper introduces a task-oriented federated meta-learning framework over NOMA networks, utilizing a novel value of learning metric and deep Q-network optimization to enhance personalized device training.

Contribution

It proposes a new VoL metric and a TLW-based optimization approach for personalized federated meta-learning in NOMA networks, addressing non-convex challenges.

Findings

Outperforms baseline schemes in simulations

Effectively personalizes device training

Demonstrates the benefits of VoL and TLW metrics

Abstract

Federated Learning (FL) has gained significant attention in recent years due to its distributed nature and privacy preserving benefits. However, a key limitation of conventional FL is that it learns and distributes a common global model to all participants, which fails to provide customized solutions for diverse task requirements. Federated meta-learning (FML) offers a promising solution to this issue by enabling devices to finetune local models after receiving a shared meta-model from the server. In this paper, we propose a task-oriented FML framework over non-orthogonal multiple access (NOMA) networks. A novel metric, termed value of learning (VoL), is introduced to assess the individual training needs across devices. Moreover, a task-level weight (TLW) metric is defined based on task requirements and fairness considerations, guiding the prioritization of edge devices during FML training. The formulated problem, to maximize the sum of TLW-based VoL across devices, forms a non-convex mixed-integer non-linear programming (MINLP) challenge, addressed here using a parameterized deep Q-network (PDQN) algorithm to handle both discrete and continuous variables. Simulation results demonstrate that our approach significantly outperforms baseline schemes, underscoring the advantages of the proposed framework.