paper-with-me

홈 › Papers

Robust Federated Learning in the Face of Covariate Shift: A Magnitude Pruning with Hybrid Regularization Framework for Enhanced Model Aggregation

2024-12-19 · Ozgu Goksu, Nicolas Pugeault

The development of highly sophisticated neural networks has allowed for fast progress in every field of computer vision, however, applications where annotated data is prohibited due to privacy or security concerns remain challenging. Federated Learning (FL) offers a promising framework for individuals aiming to collaboratively develop a shared model while preserving data privacy. Nevertheless, our findings reveal that variations in data distribution among clients can profoundly affect FL methodologies, primarily due to instabilities in the aggregation process. We also propose a novel FL framework to mitigate the adverse effects of covariate shifts among federated clients by combining individual parameter pruning and regularization techniques to improve the robustness of individual clients' models to aggregate. Each client's model is optimized through magnitude-based pruning and the addition of dropout and noise injection layers to build more resilient decision pathways in the networks and improve the robustness of the model's parameter aggregation step. The proposed framework is capable of extracting robust representations even in the presence of very large covariate shifts among client data distributions and in the federation of a small number of clients. Empirical findings substantiate the effectiveness of our proposed methodology across common benchmark datasets, including CIFAR10, MNIST, SVHN, and Fashion MNIST. Furthermore, we introduce the CelebA-Gender dataset, specifically designed to evaluate performance on a more realistic domain. The proposed method is capable of extracting robust representations even in the presence of both high and low covariate shifts among client data distributions.

📄 PDF Abstract BibTeX arXiv:2412.15010

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Federated Covariate Shift Adaptation for Missing Target Output Values

2023-02-28 · Yaqian Xu, Wenquan Cui, Jianjun Xu, Haoyang Cheng

The most recent multi-source covariate shift algorithm is an efficient hyperparameter optimization algorithm for missing target output. In this paper, we extend this algorithm to the framework of federated learning. For …

Domain AdaptationFederated LearningHyperparameter Optimization

Federated Learning under Covariate Shifts with Generalization Guarantees

2023-06-08 · Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick, Grigorios Chrysos 외

This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training …

Federated Learning

Overcoming the Challenges of Batch Normalization in Federated Learning

2024-05-23 · Rachid Guerraoui, Rafael Pinot, Geovani Rizk, John Stephan 외

Batch normalization has proven to be a very beneficial mechanism to accelerate the training and improve the accuracy of deep neural networks in centralized environments. Yet, the scheme faces significant challenges in fe…

Federated Learning

PIcsC: Partitioning-Induced Covariate Shift Correction

2026-07-28 · Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari, Tahir Qasim Syed arxiv

Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated learning. We propose \textit{Partition-Induced Covariate-shift Correct…

Federated Learning

Technical note on Fisher Information for Robust Federated Cross-Validation

2025-10-04 · Behraj Khan, Tahir Qasim Syed arxiv

When training data are fragmented across batches or federated-learned across different geographic locations, trained models manifest performance degradation. That degradation partly owes to covariate shift induced by dat…

Federated Learning