Xiaomin Ouyang, Zhiyuan Xie, Heming Fu, Sitong Cheng, Neiwen Ling, Guoliang Xing, Jiayu Zhou, and Jianwei Huang. Harmony: Heterogeneous Multi-Modal Federated Learning through Disentangled Model Training. In The 21th Annual International Conference on Mobile Systems, Applications, and Services (Acceptance rate: 41/198=20.7%), 2023
Harmony: Heterogeneous Multi-Modal Federated Learning through Disentangled Model Training
Harmony, a new system for heterogeneous multi-modal federated learning. Harmony disentangles the multi-modal network training in a novel two-stage framework, namely modality-wise federated learning and federated fusion learning.