FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning

arXiv:2605.22898v1 Announce Type: new Abstract: Federated learning protocols face a structural trilemma: canonical server-based aggregationite{mcmahan2017} creates a single point of failure and gradient inversion risk; decentralised ring-gossip alternativesite{hu2019segmented} expose classification heads to semi-honest peers via uninformed uniform weights; and personalised methods~ite{collins2021exploiting} reintroduce central aggregation. No existing protocol simultaneously achieves server-free operation, permanently private heads, ring topology, and principled asymmetric neighbour weighting. We propose FIRMA (extbf{FI}bonacci extbf{R}ing extbf{M}odel extbf{A}ggregation), a family of three progressively enhanced federated learning protocols: 1) fibfl establishes the foundation: server-free ring aggregation with Fibonacci-weighted neighbour blending and permanently private classification heads. 2) fibflp augments this with accuracy-gated neighbour suppression, selectively down-weighting poorly-converged peers while preserving the Fibonacci directional bias. 3) fibflpp, the full system, completes the family with a 2-opt ring permutation that maximises adjacent-client class diversity, global ring coverage via K_g{=}lceil N/2rceil gossip passes, and cosine-annealed self-retention calibration. We establish a convergence rate bound and three supporting propositions governing normalisation, coverage, retention, and diversity optimality. Systematic experiments across 28 configurations -- four benchmarks crossed with seven heterogeneity regimes -- demonstrate that fibflpp surpasses fedavg in all 12 label-skew configurations, with a peak advantage of +20.7,pp on CIFAR-10 at K{=}1. Under Dirichlet heterogeneity, fibflpp is the Pareto-dominant method among all server-free protocols, achieving the highest accuracy in 17 of 28 configurations.

Source: arXiv cs.LG | 2026-05-25