Towards Model Agnostic Federated Learning Using Knowledge Distillation. (arXiv:2110.15210v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2110.15210

Is it possible to design an universal API for federated learning using which
an ad-hoc group of data-holders (agents) collaborate with each other and
perform federated learning? Such an API would necessarily need to be
model-agnostic i.e. make no assumption about the model architecture being used
by the agents, and also cannot rely on having representative public data at
hand. Knowledge distillation (KD) is the obvious tool of choice to design such
protocols. However, surprisingly, we show that most natural …

arxiv distillation federated learning knowledge learning model