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

• URL: http://arxiv.org/abs/2605.22898v1
• Date: Thu, 21 May 2026 16:06:00 GMT
• Title: FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
• Abstract summary: Federated learning protocols face a structural trilemma: canonical server-based aggregation creates a single point of failure and gradient inversion risk.<n>No existing protocol simultaneously achieves server-free operation, permanently private heads, ring topology, and principled asymmetric neighbour weighting.<n>We propose FIRMA (textbfFIbonacci textbfModel textbfAggregation), a family of three progressively enhanced federated learning protocols.
• Score: 2.142974047772686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning protocols face a structural trilemma: canonical server-based aggregation~\cite{mcmahan2017} creates a single point of failure and gradient inversion risk; decentralised ring-gossip alternatives~\cite{hu2019segmented} expose classification heads to semi-honest peers via uninformed uniform weights; and personalised methods~\cite{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 (\textbf{FI}bonacci \textbf{R}ing \textbf{M}odel \textbf{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 $K_g{=}\lceil N/2\rceil$ 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.

Related papers

• Federated Causal Discovery via Regression-Directed Cumulants [3.5337024739132197]
  We study linear non-Gaussian acyclic models (LiNGAM) when used in federated environments.<n>We introduce the FedRCD family of causal discovery algorithms.
  arXiv  Detail & Related papers  (2026-09-03T11:43:29Z)
• Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients [22.724544289853558]
  FedSLM is a parameter-centric framework for federated fine-tuning with heterogeneous compressed clients.<n>We provide theoretical guarantees for adapter-level aggregation, subspace-alignment bounds for cross-group fusion, and a characterization of how the confidence loss mitigates weak-supervision noise.
  arXiv  Detail & Related papers  (2026-07-31T06:45:56Z)
• OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization [58.03221830946145]
  We propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes.<n>We show that OmniISR consistently improves model performance in both centralized and federated paradigms.
  arXiv  Detail & Related papers  (2026-05-19T04:13:27Z)
• Fed-BAC: Federated Bandit-Guided Additive Clustering in Hierarchical Federated Learning [4.998584084394827]
  This paper proposes Fed-BAC, which integrates additive cluster personalization with a two-level bandit framework.<n>Fed-BAC achieves distributed accuracy gains of up to +35.5pp over HierFAVG and +8.4pp over IFCA.
  arXiv  Detail & Related papers  (2026-05-12T09:07:52Z)
• DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency [12.06248193140353]
  Contrastive language-image preCLIP suffers from two structural weaknesses.<n>RANKCLIP partially addresses the first issue with a list-wise Plackett-Luce ranking-consistency loss.<n>We propose DINORANKCLIP, a pretraining framework that addresses both jointly.
  arXiv  Detail & Related papers  (2026-05-07T17:19:52Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• DiffGRM: Diffusion-based Generative Recommendation Model [63.35379395455103]
  Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID)<n>We propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM)<n> Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets.
  arXiv  Detail & Related papers  (2025-10-21T03:23:32Z)
• Error Feedback for Muon and Friends [80.90330715662961]
  We introduce EF21-Muon, the first communication-efficient, non-Euclidean LMO-based with rigorous convergence guarantees.<n>Our theory covers non-Euclidean smooth and the more general $(L0, L1)$-smooth setting, matching best-known Euclidean rates and enabling faster convergence under suitable norm choices.
  arXiv  Detail & Related papers  (2025-10-01T08:20:08Z)
• Variational Gaussian Mixture Manifold Models for Client-Specific Federated Personalization [0.0]
  VGM$2$ is a geometry-centric PFL framework that learns client-specific parametric UMAP embeddings.<n>Each client maintains a Dirichlet-Normal-Inverse-Gamma posterior over marker weights, means, and variances.<n>VGM$2$ achieves competitive or superior test F1 scores compared to strong baselines.
  arXiv  Detail & Related papers  (2025-09-04T01:28:02Z)
• Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers [24.88026399458157]
  Byzantine machine learning has garnered considerable attention in light of the unpredictable faults that can occur. The key to secure machines in distributed learning is resilient aggregation mechanisms.
  arXiv  Detail & Related papers  (2023-12-20T08:36:55Z)
• Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework [60.981406394238434]
  We propose a general framework of adversarial certification with non-Gaussian noise and for more general types of attacks. Our proposed methods achieve better certification results than previous works and provide a new perspective on randomized smoothing certification.
  arXiv  Detail & Related papers  (2020-02-21T07:52:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.