In some applications, edge learning is experiencing a shift in focusing from
conventional learning from scratch to new two-stage learning unifying
pre-training and task-specific fine-tuning. This paper considers the problem of
joint communication and computation resource management in a two-stage edge
learning system. In this system, model pre-training is first conducted at an
edge server via centralized learning on local pre-stored general data, and then
task-specific fine-tuning is performed at edge devices based on the pre-trained
model via federated edge learning. For the two-stage learning model, we first
analyze the convergence behavior (in terms of the average squared gradient norm
bound), which characterizes the impacts of various system parameters such as
the number of learning rounds and batch sizes in the two stages on the
convergence rate. Based on our analytical results, we then propose a joint
communication and computation resource management design to minimize an average
squared gradient norm bound, subject to constraints on the transmit power,
overall system energy consumption, and training delay. The decision variables
include the number of learning rounds, batch sizes, clock frequencies, and
transmit power control for both pre-training and fine-tuning stages. Finally,
numerical results are provided to evaluate the effectiveness of our proposed
design. It is shown that the proposed joint resource management over the
pre-training and fine-tuning stages well balances the system performance
trade-off among the training accuracy, delay, and energy consumption. The
proposed design is also shown to effectively leverage the inherent trade-off
between pre-training and fine-tuning, which arises from the differences in data
distribution between pre-stored general data versus real-time task-specific
data, thus efficiently optimizing overall system performance.

在边缘学习系统中，本文研究了双阶段学习中的联合通信和计算资源管理问题，分析了系统参数对收敛速率的影响，并提出了一个联合资源管理设计来优化系统性能。该设计充分利用了预训练和微调之间的固有权衡，有效地优化整体系统性能。

边缘学习中资源管理的重新思考：一种联合预训练和微调的设计范式

Rethinking Resource Management in Edge Learning: A Joint Pre-training  and Fine-tuning Design Paradigm

This paper presents a novel and effective deep reinforcement learning
(DRL)-based approach to addressing joint resource management (JRM) in a
practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where
hardware sensitivity and imperfect successive interference cancellation (SIC)
are considered. We first formulate the JRM problem to maximize the weighted-sum
system throughput. Then, the JRM problem is decoupled into two iterative
subtasks: subcarrier assignment (SA, including user grouping) and power
allocation (PA). Each subtask is a sequential decision process. Invoking a deep
deterministic policy gradient algorithm, our proposed DRL-based JRM (DRL-JRM)
approach jointly performs the two subtasks, where the optimization objective
and constraints of the subtasks are addressed by a new joint reward and
internal reward mechanism. A multi-agent structure and a convolutional neural
network are adopted to reduce the complexity of the PA subtask. We also tailor
the neural network structure for the stability and convergence of DRL-JRM.
Corroborated by extensive experiments, the proposed DRL-JRM scheme is superior
to existing alternatives in terms of system throughput and resistance to
interference, especially in the presence of many users and strong inter-cell
interference. DRL-JRM can flexibly meet individual service requirements of
users.

本文提出了基于深度强化学习的联合资源管理方法来应对多载波非正交多址系统中的硬件敏感性和不完美连续干扰消除，包括对子载波赋值和功率分配两个迭代子任务的决策过程。经过广泛实验验证，该方法在系统吞吐量和抗干扰能力方面较现有替代方案更加优越，并可以灵活满足用户的个性化服务要求。