Federated learning (FL) mechanisms typically require each client to transfer their weights to a central server, irrespective of how useful they are. In order to avoid wasteful data transfer costs from clients to the central server, we propose the use of consensus based protocols to identify a subset of clients with most useful model weights at each data transfer step. First, we explore the application of existing fluid democracy protocols to FL from a performance standpoint, comparing them with traditional one-person-one-vote (also known as 1p1v or FedAvg). We propose a new fluid democracy protocol named viscous-retained democracy that always does better than 1p1v under the same assumptions as existing fluid democracy protocols while also not allowing for influence accumulation. Secondly, we identify weaknesses of fluid democracy protocols from an adversarial lens in terms of their dependence on topology and/ or number of adversaries required to negatively impact the global model weights. To this effect, we propose an algorithm (FedVRD) that dynamically limits the effect of adversaries while minimizing cost by leveraging the delegation topology.

Even in the first month of my governorship of this fine state, I began to have problems with the legislature, which belonged to the "other" political party. I had campaigned on the plan to transform the state capital, Columbville, into a Smart City, but my political party and the opposition wanted it to use different operating systems. Another problem was that we disagreed about what should be done with the three abandoned shopping centers, now that all our citizens bought their stuff online. That issue was tangled up with all the road improvements needed to keep the self-driving trucks and taxis from roaming the schoolyards, although that could have been worse if the kids were still attending classes rather than home-schooling online as most of them now did. I sent drafts of laws and budgets to the legislature, and they voted them down.