The research area is witnessing a significant shift towards leveraging advanced machine learning techniques, particularly federated learning (FL), to address complex challenges in public health and mobile network management. FL is being increasingly adopted for its ability to enable collaborative model training across decentralized data sources while preserving privacy, which is crucial for sensitive data like health records and traffic patterns. In the context of epidemics, FL frameworks are being developed to predict the spread of diseases by integrating spatio-temporal data from multiple isolated networks, enhancing the robustness and accuracy of epidemic forecasts. This approach not only addresses privacy concerns but also improves the ability to capture dynamic dependencies in epidemic processes. In mobile networks, FL is being explored as a solution for traffic forecasting, offering a distributed and privacy-preserving method to enhance real-time resource allocation. Studies in this area are focusing on optimizing model aggregation techniques, managing outliers, and integrating exogenous data sources to improve prediction accuracy and environmental sustainability. Overall, the field is progressing towards more sophisticated and privacy-conscious solutions that promise to advance both public health management and mobile network efficiency.

Noteworthy papers include one that formulates epidemic prediction as a submodular optimization problem, offering a novel approach to minimizing infection probabilities while managing intervention costs. Another paper stands out for its comprehensive case study on FL in mobile networks, highlighting its potential as a robust solution for traffic forecasting, emphasizing both privacy and environmental sustainability.