Federated Learning (FL) is a machine learning paradigm allowing collaborative model training across distributed nodes (clients) while preserving data privacy and security. However, effectively monitoring client behavior and evaluating contributions within FL environments remain significant challenges that need to be addressed. In this study, we demonstrate the scalability and robustness of the eccentricity analysis-based approach for monitoring client behavior in the FL setting through extensive experimentation, particularly in non-IID data scenarios. Our results show that clients' eccentricity signatures can be used for analyzing clients' behavioral patterns and understanding their contributions to the shared model. 

This work focuses on improving the performance and fairness of Federated Learning (FL) in non-IID settings by enhancing model aggregation and boosting the training of under-performing clients. We propose FedABoost, a novel FL framework that integrates a dynamic boosting mechanism and an adaptive gradient aggregation strategy. Inspired by the weighting mechanism of the Multiclass AdaBoost (SAMME) algorithm, our aggregation method assigns higher weights to clients with lower local error rates, thereby promoting more reliable contributions to the global model. In parallel, FedABoost dynamically boosts under-performing clients by adjusting the focal loss focusing parameter, emphasizing hard-to-classify examples during local training. These mechanisms work together to enhance the global model’s fairness by reducing disparities in client performance and encouraging fair participation. We have evaluated FedABoost on three benchmark datasets: MNIST, FEMNIST, and CIFAR10, and compared its performance with those of FedAvg and Ditto. The results show that FedABoost achieves improved fairness and competitive performance. The FedABoost code and the experimental results are available at \href{https://github.com/tharukackasthuri/fedaboost.git}{GitHub}

Federated Learning (FL) is a promising distributed learning method that enables multiple clients to collaboratively train a shared model without sharing their raw data thus preserving privacy. However, in practical implementations, client data are typically non-independent and identically distributed (non-IID). This resulting in heterogeneous learning dynamics and unequal benefits across participants. Improvements in average global performance can mask performance degradation for disadvantaged clients, highlighting a structural fairness challenge in FL. This thesis argues that achieving fairness under non-IID FL requires explicit understanding and modeling of client behavioral heterogeneity rather than uniform aggregation of client updates. 

In addressing the issue of fairness in FL under data heterogeneity, the thesis first studies and analyzes clients' deviating behavior during the federated training process. An eccentricity-based approach is introduced to quantify deviations in local models and data representations within the global model, enabling systematic identification of atypical contribution and benefit patterns. The insights gained lay the foundation for our further research into developing novel, fairness-aware FL solutions for heterogeneous, distributed learning setups.

Then it proposes a fairness-aware aggregation framework called FeDABoost that adapts client influence based on local performance signals. By dynamically weighting client updates and adjusting local optimization to emphasize hard examples, the method reduces disparities across heterogeneous clients while maintaining competitive global performance. Later, the thesis introduces DEFFT, a clients distribution-aware framework that models latent similarities among clients through persistent grouping based on label distributions. Cluster-level models and hierarchical knowledge distillation integrate inter-client structure into the learning process, enhancing fairness metrics along with overall accuracy.

Across multiple benchmark datasets, the proposed approaches demonstrate that a principled way to modeling heterogeneity can lead to measurable improvements in fairness without compromising global performance. The three discussed studies together establish a structured framework for mitigating unequal benefits in FL under non-IID data distributions.

The success of Federated Learning (FL) hinges upon the active participation and contributions of edge devices as they collaboratively train a global model while preserving data privacy. Understanding the behavior of individual clients within the FL framework is essential for enhancing model performance, ensuring system reliability, and protecting data privacy. However, analyzing client behavior poses a significant challenge due to the decentralized nature of FL, the variety of participating devices, and the complex interplay between client models throughout the training process. This research proposes a novel approach based on eccentricity analysis to address the challenges associated with understanding the different clients' behavior in the federation. We study how the eccentricity analysis can be applied to monitor the clients' behaviors through the training process by assessing the eccentricity metrics of clients' local models and clients' data representation in the global model. The Kendall ranking method is used for evaluating the correlations between the defined eccentricity metrics and the clients' benefit from the federation and influence on the federation, respectively. Our initial experiments on a publicly available data set demonstrate that the defined eccentricity measures can provide valuable information for monitoring the clients' behavior and eventually identify clients with deviating behavioral patterns. © 2024 IEEE.

Federated Learning (FL) on heterogeneous data often leads to performance disparities across clients, where improvements in average accuracy may mask degradation for disadvantaged clients. Most existing FL frameworks treat all clients as homogeneous participants, ignoring latent similarities in their data distributions.In this study, we introduce a fairness-aware FL framework, DEFFT, which is specifically designed to enhance both global performance and fairness among clients. DEFFT identifies the distributional structure among clients based on label distributions, creating persistent client groups that reflect data similarities. For each of these groups, a cluster-level model is created using size-aware aggregation. Simultaneously, the global model is formed by aggregating all client updates using weights determined by both local dataset size and cluster priority scores derived from smoothed cluster losses. The cluster model serves as the teacher, while each client model, initialized from the global model, acts as the student during local optimization within a hierarchical knowledge distillation scheme. We evaluate DEFFT on MNIST, CIFAR-10, and FEMNIST, demonstrating improved fairness metrics and competitive global accuracy compared to FedAvg and q-FedAvg.