Supernet Training for Federated Image Classification under System Heterogeneity. (arXiv:2206.01366v4 [cs.LG] UPDATED)

Efficient deployment of deep neural networks across many devices and resource
constraints, especially on edge devices, is one of the most challenging
problems in the presence of data-privacy preservation issues. Conventional
approaches have evolved to either improve a single global model while keeping
each local training data decentralized (i.e., data-heterogeneity) or to train a
once-for-all network that supports diverse architectural settings to address
heterogeneous systems equipped with different computational capabilities (i.e.,
model-heterogeneity). However, little research has considered both directions
simultaneously. …

arxiv classification image lg training