FEDERATED LEARNING AMIDST DYNAMIC ENVIRONMENTS

Federated Learning (FL) is a prime example of a large-scale distributed machine learning framework that has emerged as a result of the exponential growth in data generation and processing capabilities on smart devices. This framework enables the efficient processing and analysis of vast amounts of data, leveraging the collective power of numerous devices to achieve unprecedented scalability and performance. In the FL framework, each end-user device trains a local model using its own data. Through the periodic synchronization of local models, FL achieves a global model that incorporates the insights from all participat- ing devices. This global model can then be used for various applications, such as predictive analytics, recommendation systems, and more.

Despite its potential, traditional Federated Learning (FL) frameworks face significant hur- dles in real-world applications. These challenges stem from two primary issues: the dynamic nature of data distributions and the efficient utilization of network resources in diverse set- tings. Traditional FL frameworks often rely on the assumption that data distributions remain stationary over time. However, real-world environments are inherently dynamic, with data distributions constantly evolving, which in turn becomes a potential source of temporal het- erogeneity in FL. Another significant challenge in traditional FL frameworks is the efficient use of network resources in heterogeneous settings. Real-world networks consist of devices with varying computational capabilities, communication protocols, and network conditions. Traditional FL frameworks often struggle to adapt to these diverse spatially heterogeneous settings, leading to inefficient use of network resources and increased latency.

The primary focus of this thesis is to investigate algorithmic frameworks that can miti- gate the challenges posed by temporal and spatial system heterogeneities in FL. One of the significant sources of temporal heterogeneities in FL is owed to the dynamic drifting of client datasets over time, whereas spatial heterogeneities majorly broadly subsume the diverse computational capabilities and network conditions of devices in a network. We introduce two novel FL frameworks: MASTER-FL, which addresses model staleness in the presence of temporally drifting datasets, and Cooperative Edge-Assisted Dynamic Federated Learning CE-FL, which manages both spatial and temporal heterogeneities in extensive hierarchical FL networks. MASTER-FL is specifically designed to ensure that the global model remains accurate and up-to-date even in environments which are characterized by rapidly changing datasets across time. CE-FL, on the other hand, leverages server-side computing capabili- ties, intelligent data offloading, floating aggregation and cooperative learning strategies to manage the diverse computational capabilities and network conditions often associated with modern FL systems.