MIP: CLIP-based Image Reconstruction from PEFT Gradients

no code implementations • 26 Feb 2024 • Peiheng Zhou, Ming Hu, Xiaofei Xie, Yihao Huang, Kangjie Chen, Mingsong Chen

Contrastive Language-Image Pre-training (CLIP) model, as an effective pre-trained multimodal neural network, has been widely used in distributed machine learning tasks, especially Federated Learning (FL).

Federated Learning Image Reconstruction +1

FedCross: Towards Accurate Federated Learning via Multi-Model Cross Aggregation

no code implementations • 15 Oct 2022 • Ming Hu, Peiheng Zhou, Zhihao Yue, Zhiwei Ling, Yihao Huang, Yang Liu, Mingsong Chen

Due to the remarkable performance in preserving data privacy for decentralized data scenarios, Federated Learning (FL) has been considered as a promising distributed machine learning paradigm to deal with data silos problems.

Federated Learning