Tag
本文提出 DeFiRank，一个基于联邦学习的成对排序框架，使多家金融机构在不共享私有交易数据的情况下协作训练治理排序模型，在真实区块链数据上接近集中式基线的排序性能，同时保障数据隐私。
FedAlphaEdit 提出了首个在本地编辑与服务器端合并规则上统一遵循零空间原则的协作式知识编辑框架，使无法共享原始编辑数据的机构能够联合维护共享模型，其编辑成功率与知识保留能力接近集中式编辑水平。
提出一种基于轻量级时序Transformer CAN编码器与联邦学习轻量头部的隐私保护框架，用于检测车内网络中的细微时序与上下文异常，无需交换原始CAN数据即可提升共享模型。
FedRSPO+：一种面向决策聚焦联邦学习的异构感知框架，基于 RSPO+ 正则化预测-优化替代损失，通过平滑决策映射在客户端目标与约束异构时保持稳定优化，并给出随异构程度缩放、在同构时消失的跨客户端误差界。
This arXiv paper introduces a role-aware Decider-Supervisor framework combining centralized ML, a FedAvg-trained federated meta-model, and Base/QLoRA LLM variants with blockchain auditability, finding that AI supervision only reduces fraud-decision errors under specific roles, calibration, and traffic conditions rather than by default.
Google Research introduces a new TEE-based federated learning system that provides fully verifiable and auditable privacy guarantees (remote attestation, confidentiality, integrity) with improved accuracy, now adopted by Gboard for faster compute.
The paper introduces FedCORE, a federated adaptation framework that jointly couples multimodal encoder perception and graph neural network reasoning via a shared low-dimensional latent state, reducing the encoder-GNN pairing gap by 80.7% on decentralized multimodal graphs.
This paper proposes EN-HMTFL, an encoder-sharing hierarchical multi-task federated learning framework for vehicular ad hoc networks that lets vehicles train heterogeneous perception tasks collaboratively via a shared encoder while keeping task-specific decoders local, improving accuracy by up to 24% and reducing communication rounds by up to 28.8%.
The paper introduces FLIP (Federated Learning Interoperability Platform), an open-source multi-application platform that makes cross-continental federated learning in healthcare repeatable, demonstrated via federated fine-tuning and evaluation on synthetic chest X-ray cohorts across UK and Thailand nodes.
A matched-protocol comparison of synchronous ring gossip, FedAvg, local and centralized training for LSTM failure detectors on the NASA C-MAPSS turbofan benchmark, showing gossip as a practical serverless alternative to federated averaging that matches FedAvg performance without a coordinator.
This paper introduces the first federated targeted maximum likelihood estimation (TMLE) algorithm, enabling collaborative statistical inference across institutions without sharing raw data, while addressing privacy and communication efficiency.
The paper introduces FAVoR, a method to measure and mitigate the loss of author-specific writing styles in federated learning for personalized language model adaptation, addressing the problem of author-style homogenization.
This paper provides a comprehensive survey of robustness in federated learning, covering threat models, aggregation strategies, defensive tactics, and future research directions.
The paper introduces a federated learning framework for Averaged n-Dependence Estimators (AnDE) classifiers, enhancing privacy by avoiding transmission of semantically meaningful parameters and demonstrating effectiveness on discrete datasets.
A new free and open-source decision model from FLock.io, comparable to Jev, offers fast and error-free inference for various applications with a typed decision approach.
This paper proposes a practical recipe for semi-supervised federated ASR using online pseudo-labels with server update stabilization, demonstrating significant improvements over prior methods in both in-domain and cross-domain settings.
This paper evaluates federated learning for privacy-preserving hybrid quantum-classical machine learning, demonstrating improved accuracy over local training while reducing communication and maintaining parameter efficiency.
The paper proposes FedRepRAG, a decentralized retrieval-augmented generation framework that exchanges latent representations instead of raw content to reduce computational overhead and improve privacy in sensitive domains like healthcare.
The paper introduces FedeRage, a risk-averse federated learning method that uses conditional value-at-risk to address unknown client participation and heterogeneity, demonstrating enhanced accuracy, fairness, and convergence in experiments.
The paper introduces a Hegselmann-Krause opinion dynamics approach for coalition formation in federated learning to address data heterogeneity in IoT systems, achieving significant error reduction in water consumption forecasting.