Continual Distributed Learning for Crisis Management
This work addresses the challenge of real-time disaster response using social media data, but it appears incremental as it combines existing techniques like federated averaging and regularization without introducing a fundamentally new approach.
The paper tackled the problem of processing noisy, unordered social media data for crisis management by developing a low-resource continual learning system, achieving robustness through distributed learning and regularization to mitigate catastrophic forgetting.
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.