Continual Distributed Learning for Crisis Management

TL;DR

This paper proposes a low-resource, continual distributed learning system for crisis management using social media data, combining federated learning and regularization to handle noisy, evolving information during disasters.

Contribution

It introduces a novel framework integrating distributed learning, federated averaging, and regularization to improve crisis response models under resource constraints.

Findings

Effective in handling noisy social media data during crises

Reduces resource usage with distributed learning approach

Mitigates catastrophic forgetting in neural networks

Abstract

Social media platforms such as Twitter, Facebook etc can be utilised as an important source of information during disaster events. This information can be used for disaster response and crisis management if processed accurately and quickly. However, the data present in such situations is ever-changing, and using considerable resources during such a crisis is not feasible. Therefore, we have to develop a low resource and continually learning system that incorporates text classification models which are robust against noisy and unordered data. We utilised Distributed learning which enabled us to learn on resource-constrained devices, then to alleviate catastrophic forgetting in our target neural networks we utilized regularization. We then applied federated averaging for distributed learning and to aggregate the central model for continual learning.