EdgeDRM learns neighbor-only expert referral for decentralized federated learning
Queries move only between neighboring clients, and only visited clients contribute to the final prediction.
3 stories, newest first · one card per story
Queries move only between neighboring clients, and only visited clients contribute to the final prediction.
A paper gives decentralized agents a way to learn team policies from delayed shared observations.
Researchers show colluding nodes in decentralized federated learning can reconstruct private updates despite secure aggregation, using lattice-based attacks tied to the Hidden Subset Sum Problem.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views