FedAvgen: Metadata for Model Aggregation In Communication Systems

2025/04/28 by Anthony Kiggundu, Kiggundu, Anthony, Dennis Krummacker +3
Computer Science · Engineering · #Advanced Data and IoT Technologies #Artificial Intelligence (cs.AI) #Big Data and Digital Economy #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2505.05486

openalex publication_date 2025/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

To improve business efficiency and minimize costs, Artificial Intelligence (AI) practitioners have adopted a shift from formulating models from scratch towards sharing pretrained models. The pretrained models are then aggregated into a global model with higher generalization capabilities, which is afterwards distributed to the client devices. This approach is known as federated learning and inherently utilizes different techniques to select the candidate client models averaged to obtain the global model. This approach, in the case of communication systems, faces challenges arising from the existential diversity in device profiles. The multiplicity in profiles motivates our conceptual assessment of a metaheuristic algorithm (FedAvgen), which relates each pretrained model with its weight space as metadata, to a phenotype and genotype, respectively. This parent-child genetic evolution characterizes the global averaging step in federated learning. We then compare the results of our approach to two widely adopted baseline federated learning algorithms like Federated Averaging (FedAvg) and Federated Stochastic Gradient Descent (FedSGD).

Citations

• Checkpoint Merging via Bayesian Optimization in LLM Pretraining
• Optimizing the Collaboration Structure in Cross-Silo Federated Learning
• Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
• Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients
• Papaya: Practical, Private, and Scalable Federated Learning
• Device Scheduling and Update Aggregation Policies for Asynchronous Federated Learning
• Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data
• Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregations
• Fast-Convergent Federated Learning with Adaptive Weighting
• Dynamic Fusion based Federated Learning for COVID-19 Detection
• Asynchronous Decentralized SGD with Quantized and Local Updates
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Revisiting Distributed Synchronous SGD
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Non-negative matrix factorization with sparseness constraints

Related

• FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning
• FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors