TL;DR
This work proposes a similarity-based algorithm, FedKNN, which utilizes similarity between clients as part of the aggregation and restricts aggregation to the most similar neighborhood of the client, and represents the client networks as graph and shows that through similar neighborhood aggregation clients can benefit from the collective knowledge of the network and have flexibility in adapting to data drift.
Experiments under representative Non-IID settings on benchmark datasets show that PFLS-One achieves improved accuracy and faster convergence compared with representative baseline methods, and the convergence analysis under a non-convex objective provides theoretical support for the proposed method.
Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space using an NTK-based agreement score to characterize predictive behavior and determine a persona...
PDKD solves the problem of model drift caused by the inconsistent distribution of distillation datasets and the local data by generating personalized distillation datasets for each client while protecting client data privacy.
Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously. Thi...
This study experimentally measures the impact of non-IID data, noisy data, and fairness in client selection on model accuracy and convergence, and proposes a privacy-preserving scoring method to assess each client's contribution in FL.
This work introduces CoLEDS, a method for profiling unlabeled client datasets with minimal computational overhead that yields federatively trained models that are better aligned with individual data distributions and enables appropriate model assignment even for clients that do not participate in federated training.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
