mlsanityData to 7 Oct 2026

From Learning to Analytics: Improving Model Efficacy with Goal-Directed Client Selection

arXiv 2404.00371 ↗First posted 30 Mar 2024cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

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 data. 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 40 references that are in the map. First posted on arXiv 30 Mar 2024.

Builds on

14 of 40 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  3. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  4. 2019Federated Learning over Wireless Fading Channelscited by 178
  5. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  6. 2020TiFL: A Tier-based Federated Learning Systemcited by 95
  7. 2014Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Armscited by 78
  8. 2020An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guaranteecited by 61
  9. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 56
  10. 2021Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocationcited by 55
  11. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  12. 2021Blockchain Assisted Federated Learning over Wireless Channels: Dynamic Resource Allocation and Client Schedulingcited by 11
2 more
  1. 2020Distributed and Democratized Learning: Philosophy and Research Challengescited by 6
  2. 2020Edge-assisted Democratized Learning Towards Federated Analyticscited by 5

Built on by

Not cited yet.