Asynchronous Probability Ensembling for Federated Disaster Detection

arXiv cs.LG / 4/17/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper targets disaster decision support systems where network latency and limited accuracy hinder fast emergency handling, even when using federated learning.
It proposes a decentralized ensembling framework that exchanges class-probability vectors instead of model weights, which preserves data privacy and drastically reduces communication overhead.
The method uses asynchronous probability aggregation and feedback distillation to let heterogeneous CNN backbones collaborate without strict global synchronization.
Experiments indicate the approach improves disaster image identification performance over both single models and standard federated-learning baselines, especially under resource constraints.
Overall, the work presents a scalable, real-time–oriented federation strategy suitable for collaborative inference/training in bandwidth-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.