federated-learning

FedFIbOS proposes a Fisher importance-based method for optimal submodel selection in heterogeneous federated learning, theoretically grounded and achieving about 10% higher accuracy than state-of-the-art methods under non-IID settings.

The paper introduces pFedHGP, a personalized federated learning approach using hierarchical Gaussian processes for probabilistic modeling of heterogeneous distributed systems while preserving privacy through federated variational inference.

A NATO-backed startup, Scaleout Systems, is using small AI models and federated learning to enable drones to autonomously identify and attack targets in battlefield settings, leveraging edge computing for real-time updates.

FedPGT proposes a progressive gradient transmission scheme for vehicular federated learning to handle time-varying channels, achieving improved accuracy and reduced error in dynamic vehicular environments.

The paper proposes Adaptive Bayesian Partner Selection (ABPS), a peer-to-peer federated learning framework that adaptively selects collaboration partners using Bayesian methods to reduce communication costs while maintaining accuracy in heterogeneous healthcare settings.

This paper presents a framework for deploying consistent safety certificates in one-shot federated Bayesian models by propagating local posterior events through aggregation rules, specifically for Federated Averaging.

The paper introduces a federated stochastic bilevel optimization algorithm that uses only first-order gradients to avoid second-order matrix computations, reducing running time, and includes a novel learning rate mechanism with experimental confirmation.

The paper introduces SWB-DM, a robust aggregation method for federated learning that combines sliced Wasserstein barycenters with delayed momentum caching to handle Byzantine attacks and partial participation effectively.

This paper presents FedV-KGQA, a federated system for multi-hop question answering over vertically partitioned knowledge graphs, sharing empirical findings, design lessons, and an interactive prototype.

The paper proposes FLoKD, an adaptive knowledge-distillation framework for federated LoRA fine-tuning of LLMs over wireless networks, reducing communication overhead by 50-65% while maintaining competitive performance.

This paper introduces an adaptive phase-switching method for communication-efficient federated LoRA fine-tuning, achieving up to 40.5% round-trip savings in communication costs while maintaining model performance on large language models.

The paper proposes FedTAR, a task-aware federated fine-tuning method for MoE-based large language models that aligns local updates with task preferences to preserve expert specialization and improve performance under heterogeneous data.

The article explores the concept of decentralized AI as an alternative to centralized systems, reviewing research on federated learning and distributed computing that could enable collective ownership of AI.

This paper proposes Fed-Equilibrium, a federated learning framework that balances robustness and fairness in clinical networks using topological Pareto control to ensure minority nodes achieve convergence comparable to dominant hubs.

The paper introduces α-split, a two-pool allocation method for differential privacy in federated learning, addressing cross-component budget collapse in speech-LLMs and improving utility and security against attacks.

This paper presents a federated learning approach for indoor fire detection that addresses bandwidth constraints, Byzantine attacks, and fixed-server issues through compressed updates and a rotating coordinator.

The article introduces FANS, a hypernetwork-based framework for heterogeneous federated learning that learns a shared architecture space and uses parallel training with self-distillation to optimize model selection across diverse devices.

FedSubMuon is a communication-efficient federated fine-tuning method for LLMs that optimizes compact coefficient matrices within structured subspaces to reduce upload costs while maintaining strong performance.

CALM proposes a method for decentralized federated learning that uses class-wise agreement and label-gated disagreement modulation to handle non-IID data, improving teacher weighting and distillation trust without additional communication overhead.

This survey provides a comprehensive investigation of collaborative learning from Euclidean to graph-structured data, aiming to consolidate this emerging field and identify open challenges.