Asynchronous Probability Ensembling for Federated Disaster Detection

2026-04-15

AI Summary

This work addresses the low response efficiency and insufficient recognition accuracy in disaster decision support systems caused by network latency, high communication overhead, and challenges in synchronizing heterogeneous models. To overcome these limitations, the authors propose a decentralized asynchronous probabilistic ensemble framework that eschews the conventional federated learning reliance on synchronized model weight transmission. Instead, it exchanges class probability vectors among participants and incorporates a feedback distillation mechanism to enable efficient asynchronous collaboration among heterogeneous CNN models in a federated setting. Experimental results demonstrate that the proposed framework substantially reduces communication costs and outperforms both individual backbone models and standard federated approaches in resource-constrained disaster image recognition tasks, achieving higher accuracy, improved scalability, and enhanced privacy preservation.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Quick and accurate emergency handling in Disaster Decision Support Systems (DDSS) is often hampered by network latency and suboptimal application accuracy. While Federated Learning (FL) addresses some of these issues, it is constrained by high communication costs and rigid synchronization requirements across heterogeneous convolutional neural network (CNN) architectures. To overcome these challenges, this paper proposes a decentralized ensembling framework based on asynchronous probability aggregation and feedback distillation. By shifting the exchange unit from model weights to class-probability vectors, our method maintains data privacy, reduces communication requirements by orders of magnitude, and improves overall accuracy. This approach enables diverse CNN designs to collaborate asynchronously, enhancing disaster image identification performance even in resource-constrained settings. Experimental tests demonstrate that the proposed method outperforms traditional individual backbones and standard federated approaches, establishing a scalable and resource-aware solution for real-time disaster response.

Problem

• Federated Learning
• Disaster Detection
• Asynchronous Training
• Communication Efficiency
• Heterogeneous Models

Innovation

• asynchronous probability aggregation
• federated learning
• decentralized ensembling
• communication efficiency
• heterogeneous CNNs