Cross-Training with Multi-View Knowledge Fusion for Heterogenous Federated Learning
Z Qi, L Meng, W He, R Zhang, Y Wang, X Qi… - arXiv preprint arXiv …, 2024 - arxiv.org
Federated learning benefits from cross-training strategies, which enables models to train on
data from distinct sources to improve the generalization capability. However, the data …
data from distinct sources to improve the generalization capability. However, the data …
CoTuning: A Large-Small Model Collaborating Distillation Framework for Better Model Generalization
Z Liu, K Liu, M Guo, S Zhang, Y Wang - ACM Multimedia 2024 - openreview.net
Model compression and distillation techniques have become essential for deploying deep
learning models efficiently. However, existing methods often encounter challenges related to …
learning models efficiently. However, existing methods often encounter challenges related to …