Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality

TL;DR

This paper introduces a dual-criterion weighted aggregation method for federated learning that considers both data quantity and quality, improving global model performance amid client heterogeneity.

Contribution

It proposes a novel aggregation algorithm that adaptively weights client contributions based on data size and inferred data quality, addressing limitations of existing methods.

Findings

Outperforms existing aggregation methods on CIFAR-10.

Achieves better accuracy in visual obstacle avoidance tasks.

Demonstrates robustness to data heterogeneity.

Abstract

Federated learning (FL) has become one of the key methods for privacy-preserving collaborative learning, as it enables the transfer of models without requiring local data exchange. Within the FL framework, an aggregation algorithm is recognized as one of the most crucial components for ensuring the efficacy and security of the system. Existing average aggregation algorithms typically assume that all client-trained data holds equal value or that weights are based solely on the quantity of data contributed by each client. In contrast, alternative approaches involve training the model locally after aggregation to enhance adaptability. However, these approaches fundamentally ignore the inherent heterogeneity between different clients' data and the complexity of variations in data at the aggregation stage, which may lead to a suboptimal global model. To address these issues, this study proposes a novel dual-criterion weighted aggregation algorithm involving the quantity and quality of data from the client node. Specifically, we quantify the data used for training and perform multiple rounds of local model inference accuracy evaluation on a specialized dataset to assess the data quality of each client. These two factors are utilized as weights within the aggregation process, applied through a dynamically weighted summation of these two factors. This approach allows the algorithm to adaptively adjust the weights, ensuring that every client can contribute to the global model, regardless of their data's size or initial quality. Our experiments show that the proposed algorithm outperforms several existing state-of-the-art aggregation approaches on both a general-purpose open-source dataset, CIFAR-10, and a dataset specific to visual obstacle avoidance.