Timezone: »

 
FedHeN: Federated Learning in Heterogeneous Networks
Durmus Alp Emre Acar · Venkatesh Saligrama

Fri Jul 22 12:15 PM -- 01:15 PM (PDT) @
in Dynamic Neural Networks »

We propose a novel training recipe for federated learning with heterogeneous networks where each device can have different architectures. We introduce training with a side objective to the devices of higher complexities which allows different architectures to jointly train in a federated setting. We empirically show that our approach improves training of different architectures and leads to high communication savings compared to state-of-the-art methods.

[ Poster] 

Author Information

Durmus Alp Emre Acar (Boston University)
Venkatesh Saligrama (Boston University)

More from the Same Authors