TRUSS: Transmission-Reduced Unified-State Scaffolding under Non-Stationary Client Participation

Heterogeneous client objectives and unequal, time-varying availability create coupled sources of error in federated optimization: local drift and participation bias. Correcting both while preserving the speedup from local computation and keeping communication and memory costs low is a central challenge. We introduce Transmission-Reduced Unified-State Scaffolding (TRUSS), which addresses both with a single persistent, model-sized memory per client. The difference between this memory and the current server model supplies the correction applied at every local step. Each active client therefore exchanges one model-sized vector in each direction per round, matching FedAvg's per-round communication, and the server stores only the global model. For smooth non-convex objectives under independent participation whose probabilities may vary across clients and rounds, we establish an $O((NKR{)}^{-1/2}+R^{-1})$ stationarity bound, yielding linear speedup in the number of clients $N$ and local steps $K$, with no bounded-gradient-heterogeneity assumption and no knowledge of client inclusion probabilities or importance weighting. Experiments demonstrate the effectiveness and communication efficiency of TRUSS.