Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring. (arXiv:2206.06818v1 [cs.LG])

Attributes skew hinders the current federated learning (FL) frameworks from
consistent optimization directions among the clients, which inevitably leads to
performance reduction and unstable convergence. The core problems lie in that:
1) Domain-specific attributes, which are non-causal and only locally valid, are
indeliberately mixed into global aggregation. 2) The one-stage optimizations of
entangled attributes cannot simultaneously satisfy two conflicting objectives,
i.e., generalization and personalization. To cope with these, we proposed
disentangled federated learning (DFL) to disentangle the domain-specific and
cross-invariant …

aggregation arxiv diversity federated learning learning lg skew