Client Contribution Normalization for Enhanced Federated Learning

Mobile devices, including smartphones and laptops, generate decentralized and heterogeneous data, presenting significant challenges for traditional centralized machine learning models due to substantial communication costs and privacy risks. Federated Learning (FL) offers a promising alternative by enabling collaborative training of a global model across decentralized devices without data sharing. However, FL faces challenges due to statistical heterogeneity among clients, where non-independent and identically distributed (non-IID) data impedes model convergence and performance. This paper focuses on data-dependent heterogeneity in FL and proposes a novel approach leveraging mean latent representations extracted from locally trained models. The proposed method normalizes client contributions based on these representations, allowing the central server to estimate and adjust for heterogeneity during aggregation. This normalization enhances the global model's generalization and mitigates the limitations of conventional federated averaging methods. The main contributions include introducing a normalization scheme using mean latent representations to handle statistical heterogeneity in FL, demonstrating the seamless integration with existing FL algorithms to improve performance in non-IID settings, and validating the approach through extensive experiments on diverse datasets. Results show significant improvements in model accuracy and consistency across skewed distributions. Our experiments with six FL schemes: FedAvg, FedProx, FedBABU, FedNova, SCAFFOLD, and SGDM highlight the robustness of our approach. This research advances FL by providing a practical and computationally efficient solution for statistical heterogeneity, contributing to the development of more reliable and generalized machine learning models.

Distilling Calibrated Student from an Uncalibrated Teacher

Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are pre-trained and often uncalibrated, as no calibration technique is applied to the teacher model while training. Calibration of a network measures the probability of correctness for any of its predictions, which is critical in high-risk domains. In this paper, we study how to obtain a calibrated student from an uncalibrated teacher. Our approach relies on the fusion of the data-augmentation techniques, including but not limited to cutout, mixup, and CutMix, with knowledge distillation. We extend our approach beyond traditional knowledge distillation and find it suitable for Relational Knowledge Distillation and Contrastive Representation Distillation as well. The novelty of the work is that it provides a framework to distill a calibrated student from an uncalibrated teacher model without compromising the accuracy of the distilled student. We perform extensive experiments to validate our approach on various datasets, including CIFAR-10, CIFAR-100, CINIC-10 and TinyImageNet, and obtained calibrated student models. We also observe robust performance of our approach while evaluating it on corrupted CIFAR-100C data.