Asynchronous Probability Ensembling for Federated Disaster Detection

TL;DR

This paper introduces an asynchronous probability ensembling framework for federated disaster detection that reduces communication costs, maintains data privacy, and improves accuracy in resource-constrained environments.

Contribution

It proposes a decentralized ensembling method based on probability aggregation and feedback distillation, enabling asynchronous collaboration among diverse CNNs.

Findings

Outperforms traditional federated learning in accuracy.

Reduces communication requirements by orders of magnitude.

Enhances disaster image identification in resource-limited settings.

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.