VDSV: Client Selection in Federated Learning Based on Value Density and Secondary Verification

Client selection has been widely considered in Federated Learning (FL) to reduce communication overhead while ensuring proper convergence performance. Due to data heterogeneity in FL, a representative subset of participants should take into account both intra- and inter-client diversity. While existing works usually emphasize on one of them, this paper proposes a VDSV (client selection based on Value Density and Secondary Verification) framework, which optimizes the client selection strategy from both sides. Therein, intra- and inter-client diversity are respectively measured based on a designed client data score as well as gradient distance and direction. Afterwards, a client selection model is established based on a proposed metric, called client value density. Besides, a secondary validation method is developed to dynamically tweak the current client selection and model aggregation strategies. The general idea of the above design is based on the theoretical convergence analysis and the observation that the client contribution to the global model can get changed throughout the learning process. The experimental results demonstrate that VDSV can achieve higher convergence rates and ensure comparable model performance. In specific, our method can reduce the communication rounds by an average of 37.88%, which saves noticeable communication overhead.

• Publication year

  2026

• Venue

  IEEE Transactions on Network and Service Management

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TNSM.2025.3636990
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Accelerating Federated Learning for Edge Intelligence Using Conjugated Central Acceleration With Inexact Global Line Search

  2025cited by this paper
• Optimization of Data and Model Transfer for Federated Learning to Manage Large-Scale Network

  2025cited by this paper
• Optimal Placement of the Virtualized Federated Learning Aggregation Function at the Edge

  2025cited by this paper
• Federated Learning with complete service commitment of data heterogeneity

  2025cited by this paper
• FedGA: A greedy approach to enhance federated learning with Non-IID data

  2024cited by this paper
• Learning Efficiency Maximization for Wireless Federated Learning With Heterogeneous Data and Clients

  2024cited by this paper
• Data privacy protection: A novel federated transfer learning scheme for bearing fault diagnosis

  2024cited by this paper
• TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning

  2024cited by this paper
• NQFL: Nonuniform Quantization for Communication Efficient Federated Learning

  2024cited by this paper
• A Privacy-Preserving Federated Learning Framework With Lightweight and Fair in IoT

  2024cited by this paper
• FedCLS: Class-Aware Federated Learning in a Heterogeneous Environment

  2023cited by this paper
• Communication-Efficient Personalized Federated Meta-Learning in Edge Networks

  2023cited by this paper
• Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape

  2023cited by this paper
• Client Selection in Federated Learning under Imperfections in Environment

  2022cited by this paper
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces

  2022cited by this paper
• Towards Understanding Biased Client Selection in Federated Learning

  2022cited by this paper
• Diverse Client Selection for Federated Learning via Submodular Maximization

  2022influential reference
• DELTA: Diverse Client Sampling for Fasting Federated Learning

  2022influential reference
• Federated Learning for Automatic Modulation Classification Under Class Imbalance and Varying Noise Condition

  2022cited by this paper
• FedALA: Adaptive Local Aggregation for Personalized Federated Learning

  2022cited by this paper
• Client Selection in Federated Learning: Principles, Challenges, and Opportunities

  2022cited by this paper
• Sample-level Data Selection for Federated Learning

  2021cited by this paper
• Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

  2021cited by this paper
• Federated Learning on Non-IID Data Silos: An Experimental Study

  2021cited by this paper
• Data-Aware Device Scheduling for Federated Edge Learning

  2021cited by this paper
• Heterogeneity for the Win: One-Shot Federated Clustering

  2021cited by this paper
• Model-Contrastive Federated Learning

  2021cited by this paper
• Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

  2021cited by this paper
• Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data

  2021influential reference
• Client Selection Based on Label Quantity Information for Federated Learning

  2021cited by this paper
• Dynamic defense against byzantine poisoning attacks in federated learning

  2020cited by this paper
• Addressing Class Imbalance in Federated Learning

  2020cited by this paper
• Fast-Convergent Federated Learning with Adaptive Weighting

  2020cited by this paper
• Optimal Client Sampling for Federated Learning

  2020cited by this paper
• Fast-Convergent Federated Learning

  2020cited by this paper
• Choosing the Sample with Lowest Loss makes SGD Robust

  2020cited by this paper
• SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

  2019cited by this paper
• CMFL: Mitigating Communication Overhead for Federated Learning

  2019cited by this paper
• Bayesian Nonparametric Federated Learning of Neural Networks

  2019cited by this paper
• Federated Optimization in Heterogeneous Networks

  2018cited by this paper
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

  2017cited by this paper
• Communication-Efficient Learning of Deep Networks from Decentralized Data

  2016cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Delta

  2010cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Dynamic Programming

  1993cited by this paper

• No citing papers are available for this paper.