#federated learning

try —

37 papers match

cs.LG2026

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Cheng Wei

The paper introduces TriShield, a three‑component defense that eliminates privacy backdoor reconstruction attacks in federated fine‑tuning of large language models without any loss…

#federated learning#privacy attacks#language model fine-tuning#backdoor defense
cs.LG2026

Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata

Michael Ben Ali, Imen Megdiche, André Péninou +1

The paper introduces FLAMECHE, a method that reformulates metadata‑based clustered federated learning as a distributed Expectation‑Maximization process, allowing additive server up…

#federated learning#clustered federated learning#privacy-preserving learning#distributed expectation-maximization
cs.CR2026

Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data

Pouya Rajabi, Mohsen Toorani

The paper proposes a federated learning framework for clinical EEG data that uses masking‑based secure aggregation and related cryptographic techniques to protect individual model…

#federated learning#secure aggregation#privacy preservation#clinical eeg
cs.CV2026

Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement

Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell +5

The paper proposes FedPAIE, a federated learning framework that learns individual aesthetic preferences for color grading and applies lightweight, personalized image enhancement on…

#federated learning#personalized image enhancement#color grading#privacy-preserving
cs.LG2026

FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning

Zekai Chen, Haodong Lu, Shihao Li +5

The paper introduces FedOGL, a framework for federated multimodal graph learning that mitigates catastrophic forgetting by preserving semantic and structural memory through client-…

#federated learning#graph neural networks#multimodal learning#continual learning
cs.LG2026

First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selection

Yang Jiao, Kaixuan Jiao, Kai Yang +4

The paper introduces F²CTO, a federated first-order constrained trilevel optimization algorithm for robust coreset selection across distributed edge networks, providing convergence…

#distributed optimization#trilevel optimization#coreset selection#robust learning
cs.CR2026

Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning

Hongliang Zhang, Zhongyuan Yu, Guijuan Wang +4

The paper proposes FedDAB, a two‑phase defense for federated learning that uses contrastive regularization and alignment checking to detect and exclude malicious local updates caus…

#federated learning#backdoor attacks#defense mechanisms#contrastive learning
eess.SP2026

An Informativeness-based Clustered Federated Learning Method for Reliable Traffic Prediction in Managed Wi-Fi Networks

Luca Barbieri, Gianluca Fontanesi, Lorenzo Galati Giordano +2

The paper proposes a clustered federated learning framework that selects informative AP clusters using differential entropy to improve Wi‑Fi traffic prediction while reducing commu…

#federated learning#clustered learning#wifi networks#traffic prediction
cs.GT2026

Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approach

Cengis Hasan

The paper proposes a game-theoretic mechanism for forming stable, budget‑feasible coalitions in clustered federated learning, using a transferable‑surplus model and hedonic potenti…

#federated learning#coalition formation#hedonic games#budget feasibility
cs.LG2026

FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA

Donghang Duan, Xu Zheng, Lizong Zhang +2

The paper introduces FedWeave, a federated learning framework that separates expert aggregation from router optimization to better handle heterogeneous tasks by using prototype-lev…

#federated learning#parameter-efficient fine-tuning#mixture of experts#heterogeneous tasks
cs.LG2026

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

Zhaoyang Ma, Zhihao Wu, Xin Gao +3

FedTopo introduces a method for federated learning with heterogeneous client models that shares class relation topologies instead of raw model parameters, enabling more reliable kn…

#federated learning#model heterogeneity#topology sharing#knowledge aggregation
cs.LG2026

Collaborative System Failure Prognostics via Federated Longitudinal-Survival Modeling

Fan Yang, Madelyn Weller, Dimuthu Fernando +2

The paper proposes a federated learning framework that combines longitudinal sensor representation with a client‑separable discrete‑time hazard model to predict system failures and…

#federated learning#survival analysis#prognostics#condition monitoring
cs.LG2026

PIcsC: Partitioning-Induced Covariate Shift Correction

Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari +1

The paper introduces PIcsC, a Fisher information‑based regularization method that corrects covariate shift caused by data partitioning in both centralized (e.g., cross‑validation)…

#covariate shift#federated learning#regularization#fisher information
cs.CV2026

Where Physics Meets Privacy: Federated PINNs for Privacy-Preserving Brain Tumor Biomechanical Modeling

Mahmuda Akter Sristy, Md Al-Mahfuz Chowdhury, Momota Ahsana Meem +2

The paper proposes a federated physics-informed neural network that learns patient-specific brain tumor biomechanical models from MRI data while keeping raw data on local sites, ac…

#federated learning#physics-informed neural networks#brain tumor modeling#biomechanical simulation
stat.ME2026

Studying Competing Events with Federated Cumulative Incidence Curves

Malcolm Risk, Shuang Yang, Jiang Bian +6

The paper introduces a federated learning approach for constructing non‑parametric cumulative incidence curves for competing risks without sharing patient‑level data, and applies i…

#federated learning#competing risks#cumulative incidence curves#post-market safety surveillance
cs.LG2026

Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap

Sixing Tan, Xianmin Liu

The paper introduces FedKACE, a method for federated continual learning that works without task labels and handles streaming data with overlapping classes by adaptively switching i…

#federated learning#continual learning#streaming data#class overlap
cs.CR2026

NFSA: Non-Forward Secure Aggregation with One Server via Two Layer Secret Sharing

Yufei Zhou

The paper introduces a secure aggregation protocol for federated learning that uses a two‑layer secret sharing scheme to eliminate server‑forwarded data, achieving one‑shot aggrega…

#secure aggregation#federated learning#secret sharing#privacy
cs.LG2026

Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research

Ciro Benito Raggio, Lucia Migliorelli, Nils Skupien +6

The paper proposes an adaptive encoder‑freezing technique for federated learning that reduces energy use and CO2 emissions while preserving MRI‑to‑CT conversion quality.

#federated learning#green ai#medical imaging#energy efficiency
cs.DC2026

EdgeFaaS: A Function-based Framework for Edge Computing

Neha Vadnere, Yu-Ting Wang, Yitao Chen +2

EdgeFaaS is a function‑as‑a‑service framework that abstracts heterogeneous IoT, edge, and cloud resources to run edge applications such as video analytics, federated learning, and…

#edge computing#function as a service#resource virtualization#iot
cs.LG2026

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity

Kumar Kshitij Patel, Rustem Islamov, Sebastian U Stich +3

The paper establishes tighter convergence rates for Local SGD (Federated Averaging) on general convex problems under a bounded second‑order heterogeneity assumption, and provides n…

#local sgd#federated learning#convex optimization#heterogeneous data
cs.LG2026

Mechanistic Evidence for Preserved-but-Misaligned Representations in Non-IID FedAvg

Muhammad Haseeb, Salaar Masood, Muhammad Abdullah Sohail +2

The paper investigates why federated averaging (FedAvg) performs poorly on non‑IID client data, finding that client models retain useful internal representations but these become m…

#federated learning#non-iid data#representation alignment#model sparsity
cs.CV2026

FM: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging

Shengchao Chen, Ting Shu

The paper introduces FM², a federated learning framework that trains a unified foundation model for heterogeneous multimodal medical images while preserving privacy, using dual Mix…

#federated learning#foundation models#multimodal medical imaging#privacy-preserving AI
cs.CR2026

PriEval-Protect: A Unified Framework for Privacy Evaluation and Protection in Healthcare Systems

Ilef Chebil, Asma El Hadj, Souheib Yousfi +2

The paper introduces PriEval-Protect, a two‑phase framework that assesses privacy risks in healthcare systems by combining legal compliance scoring with technical data analysis, an…

#privacy evaluation#healthcare data#regulatory compliance#federated learning
cs.LG2026

Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Scheduling

Eunjeong Jeong, Nikolaos Pappas

The paper introduces PipeCycle, a federated learning framework that groups clients into pipelined cyclic sets to overlap device recharging with training, reducing overall energy co…

#federated learning#energy harvesting#distributed training#pipeline scheduling

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.