.png){kind=icon}
.png){kind=icon}
Return
From Learning to Analytics: Improving Model Efficacy With Goal-Directed Client Selection
.png){kind=icon}
OA
AI
DOI：10.1109/TMC.2024.3383038.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Federated learning (FL) is an appealing paradigm for learning a global model among distributed clients while preserving data privacy. Driven by the demand for high-quality user experiences, evaluating the well-trained global model after the FL process is crucial. In this paper, we propose a closed-loop model analytics framework that allows for effective evaluation of the trained global model using clients' local dataset. To address the challenges posed by system and data heterogeneities in the FL process, we study a goal-directed client selection problem based on the model analytics framework by selecting a subset of clients for the model training. This problem is formulated as a stochastic multi-armed bandit (SMAB) problem. We first put forth a quick initial upper confidence bound (Quick-Init UCB) algorithm to solve this SMAB problem under the federated analytics (FA) framework. Then, we further propose a belief propagation-based UCB (BP-UCB) algorithm under the democratized analytics (DA) framework. Moreover, we derive two regret upper bounds for the proposed algorithms, which increase logarithmically over the time horizon. The numerical results demonstrate that the proposed algorithms achieve nearly optimal performance, with a gap of less than 1.44% and 3.12% under the FA and DA frameworks, respectively.
Keywords:
Training
Computational modeling
Analytical models
Servers
Data models
Numerical models
Convergence
Federated learning (FL)
federated analytics (FA)
democratized analytics (DA)
client selection
belief propagation
upper confidence bound (UCB)
Journal
IF:
9.2
Papers:
5.6K
Citations:
1.8W