SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning. (arXiv:2111.14345v2 [cs.LG] UPDATED)

Federated learning~(FL) facilitates the training and deploying AI models on
edge devices. Preserving user data privacy in FL introduces several challenges,
including expensive communication costs, limited resources, and data
heterogeneity. In this paper, we propose SPATL, an FL method that addresses
these issues by: (a) introducing a salient parameter selection agent and
communicating selected parameters only; (b) splitting a model into a shared
encoder and a local predictor, and transferring its knowledge to heterogeneous
clients via the locally customized predictor. …

aggregation arxiv federated learning learning lg transfer transfer learning