Image de couverture de livre

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pérez-Corral, Cristian, Mestre, Jose I., Fernández-Hernández, Alberto, Dolz, Manuel F., Quitana-Ortí, Enrique S.
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FedOUI: OUI-Guided Client Weighting for Federated Aggregation
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

$λ$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
par: Pérez-Corral, Cristian, et autres
Publié: (2026)

StableGrad: Backward Scale Control without Batch Normalization
par: Mestre, Jose I., et autres
Publié: (2026)

Why Adam Works Better with $β_1 = β_2$: The Missing Gradient Scale Invariance Principle
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

FedSQ: Optimized Weight Averaging via Fixed Gating
par: Pérez-Corral, Cristian, et autres
Publié: (2026)

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
par: Mestre, Jose I., et autres
Publié: (2025)

Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
par: Pérez-Corral, Cristian, et autres
Publié: (2026)

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection
par: Fernández-Hernández, Alberto, et autres
Publié: (2025)

Refresh-Scaling the Memory of Balanced Adam
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

Sinusoidal Initialization, Time for a New Start
par: Fernández-Hernández, Alberto, et autres
Publié: (2025)

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregation
par: Elbatel, Marawan, et autres
Publié: (2024)

FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
par: Wen, Tian, et autres
Publié: (2026)

FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning
par: Wang, Xinpeng, et autres
Publié: (2024)

Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging
par: Jiang, Meirui, et autres
Publié: (2023)

NAFTA'S institutions : An evaluation ten years on / Luis Quitana Romero
par: Quitana Romero, Luis

An Interpretable Client Decision Tree Aggregation process for Federated Learning
par: Argente-Garrido, Alberto, et autres
Publié: (2024)

A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning
par: Rosendal, Daan, et autres
Publié: (2026)

FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
par: Heilmann, Xenia, et autres
Publié: (2025)

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case
par: Marfo, William, et autres
Publié: (2025)

FilFL: Client Filtering for Optimized Client Participation in Federated Learning
par: Fourati, Fares, et autres
Publié: (2023)

Tackling Selfish Clients in Federated Learning
par: Augello, Andrea, et autres
Publié: (2024)

Efficient Client Selection in Federated Learning
par: Marfo, William, et autres
Publié: (2025)

Addressing Data Quality Decompensation in Federated Learning via Dynamic Client Selection
par: Fei, Qinjun, et autres
Publié: (2025)

From domain-landmark graph learning to problem-landmark graph generation
par: Pérez-Corral, Cristian, et autres
Publié: (2025)

Communication-Efficient Federated Learning with Accelerated Client Gradient
par: Kim, Geeho, et autres
Publié: (2022)

Federated Learning with Sample-level Client Drift Mitigation
par: Xu, Haoran, et autres
Publié: (2025)

Robust Client-Server Watermarking for Split Federated Learning
par: Tang, Jiaxiong, et autres
Publié: (2025)

Unlearning Clients, Features and Samples in Vertical Federated Learning
par: Varshney, Ayush K., et autres
Publié: (2025)

Robust Federated Learning against Noisy Clients via Masked Optimization
par: Jiang, Xuefeng, et autres
Publié: (2025)

Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
par: Kritharakis, Emmanouil, et autres
Publié: (2025)

RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
par: Penalva, Isaac Marroqui, et autres
Publié: (2025)

History-Aware and Dynamic Client Contribution in Federated Learning
par: Ghosh, Bishwamittra, et autres
Publié: (2024)

Trust Driven On-Demand Scheme for Client Deployment in Federated Learning
par: Chahoud, Mario, et autres
Publié: (2024)

FedZMG: Efficient Client-Side Optimization in Federated Learning
par: Zantalis, Fotios, et autres
Publié: (2026)

Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning
par: Weng, Shudi, et autres
Publié: (2025)

Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning
par: Ukaye, Asim, et autres
Publié: (2026)

Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection
par: HaghighiFard, M. Saeid, et autres
Publié: (2024)