Fine-tuning global model via data-free knowledge distillation for non-iid federated learning
Federated Learning (FL) is an emerging distributed learning paradigm under privacy
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
L Zhang, L Shen, L Ding, D Tao… - 2022 IEEE/CVF …, 2022 - computer.org
Federated Learning (FL) is an emerging distributed learning paradigm under privacy
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
L Zhang, L Shen, L Ding, D Tao, LY Duan - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Federated Learning (FL) is an emerging distributed learning paradigm under privacy
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
[PDF][PDF] Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
L Zhang, L Shen, L Ding, D Tao, LY Duan - openaccess.thecvf.com
To explore the influence of long-tailed data on model performance, we train models using
multiple subsets of CIFAR10, which have different degrees of imbalance. Here the subset is …
multiple subsets of CIFAR10, which have different degrees of imbalance. Here the subset is …
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
L Zhang, L Shen, L Ding, D Tao… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Federated Learning (FL) is an emerging distributed learning paradigm under privacy
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
L Zhang, L Shen, L Ding, D Tao, LY Duan - arXiv preprint arXiv …, 2022 - arxiv.org
Federated Learning (FL) is an emerging distributed learning paradigm under privacy
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …
constraint. Data heterogeneity is one of the main challenges in FL, which results in slow …