SOTAVerified

Federated Learning

Federated Learning is a machine learning approach that allows multiple devices or entities to collaboratively train a shared model without exchanging their data with each other. Instead of sending data to a central server for training, the model is trained locally on each device, and only the model updates are sent to the central server, where they are aggregated to improve the shared model.

This approach allows for privacy-preserving machine learning, as each device keeps its data locally and only shares the information needed to improve the model.

Papers

Showing 63516400 of 6771 papers

TitleStatusHype
Backdoor attacks and defenses in feature-partitioned collaborative learning0
Defending against Backdoors in Federated Learning with Robust Learning RateCode1
Sharing Models or Coresets: A Study based on Membership Inference Attack0
Experiments of Federated Learning for COVID-19 Chest X-ray Images0
Delay Minimization for Federated Learning Over Wireless Communication Networks0
Multi-Armed Bandit Based Client Scheduling for Federated LearningCode1
Privacy Threats Against Federated Matrix Factorization0
Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning0
On the Outsized Importance of Learning Rates in Local Update MethodsCode0
Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy0
Federated Learning with Compression: Unified Analysis and Sharp Guarantees0
Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoTCode1
FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications0
Federated Mutual LearningCode1
Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guaranteesCode0
Local Stochastic Approximation: A Unified View of Federated Learning and Distributed Multi-Task Reinforcement Learning Algorithms0
Security and Privacy Preserving Deep Learning0
Byzantine-Resilient High-Dimensional Federated Learning0
D2P-Fed: Differentially Private Federated Learning With Efficient Communication0
Exact Support Recovery in Federated Regression with One-shot Communication0
Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint LearningCode1
Scheduling Policy and Power Allocation for Federated Learning in NOMA Based MEC0
Free-rider Attacks on Model Aggregation in Federated LearningCode1
Federated Learning Meets Multi-objective OptimizationCode1
DEED: A General Quantization Scheme for Communication Efficiency in Bits0
A Better Alternative to Error Feedback for Communication-Efficient Distributed LearningCode1
FedFMC: Sequential Efficient Federated Learning on Non-iid Data0
Federated Learning With Quantized Global Model Updates0
FedCD: Improving Performance in non-IID Federated LearningCode1
Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup0
Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets0
Federated Survival Analysis with Discrete-Time Cox Models0
Byzantine-Robust Learning on Heterogeneous Datasets via BucketingCode1
Robust Federated Learning: The Case of Affine Distribution Shifts0
Personalized Federated Learning with Moreau EnvelopesCode1
Fusion Learning: A One Shot Federated Learning0
The OARF Benchmark Suite: Characterization and Implications for Federated Learning SystemsCode1
Understanding Unintended Memorization in Federated Learning0
An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averaging0
Towards Flexible Device Participation in Federated Learning0
Federated and continual learning for classification tasks in a society of devices0
FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction0
Ensemble Distillation for Robust Model Fusion in Federated LearningCode0
Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data0
Backdoor Attacks on Federated Meta-Learning0
SECure: A Social and Environmental Certificate for AI Systems0
XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning0
Distributed Learning on Heterogeneous Resource-Constrained Devices0
Locally Private Graph Neural NetworksCode1
ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret SharingCode1
Show:102550
← PrevPage 128 of 136Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SiloBN + ASAMmIoU49.75Unverified
2SiloBN + SAMmIoU49.1Unverified
3SiloBNmIoU45.96Unverified
4FedSAM + SWAmIoU43.42Unverified
5FedASAM + SWAmIoU43.02Unverified
6FedAvg + SWAmIoU42.48Unverified
7FedASAMmIoU42.27Unverified
8FedSAMmIoU41.22Unverified
9FedAvgmIoU38.65Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAAcc@1-1262Clients68.32Unverified
2FedSAM + SWAAcc@1-1262Clients68.12Unverified
3FedAvg + SWAAcc@1-1262Clients67.52Unverified
4FedASAMAcc@1-1262Clients64.23Unverified
5FedSAMAcc@1-1262Clients63.72Unverified
6FedAvgAcc@1-1262Clients61.91Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients42.64Unverified
2FedASAMACC@1-100Clients39.76Unverified
3FedSAM + SWAACC@1-100Clients39.51Unverified
4FedSAMACC@1-100Clients36.93Unverified
5FedAvgACC@1-100Clients36.74Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients41.62Unverified
2FedASAMACC@1-100Clients40.81Unverified
3FedSAM + SWAACC@1-100Clients39.24Unverified
4FedAvgACC@1-100Clients38.59Unverified
5FedSAMACC@1-100Clients38.56Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients48.72Unverified
2FedSAM + SWAACC@1-100Clients46.76Unverified
3FedASAMACC@1-100Clients46.58Unverified
4FedSAMACC@1-100Clients44.84Unverified
5FedAvgACC@1-100Clients41.27Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients48.27Unverified
2FedASAMACC@1-100Clients47.78Unverified
3FedSAM + SWAACC@1-100Clients46.47Unverified
4FedSAMACC@1-100Clients46.05Unverified
5FedAvgACC@1-100Clients42.17Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients49.17Unverified
2FedSAM + SWAACC@1-100Clients47.96Unverified
3FedASAMACC@1-100Clients45.61Unverified
4FedSAMACC@1-100Clients44.73Unverified
5FedAvgACC@1-100Clients40.43Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAM + SWAACC@1-100Clients42.01Unverified
2FedSAM + SWAACC@1-100Clients39.3Unverified
3FedASAMACC@1-100Clients36.04Unverified
4FedSAMACC@1-100Clients31.04Unverified
5FedAvgACC@1-100Clients30.25Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAMACC@1-100Clients54.97Unverified
2FedASAM + SWAACC@1-100Clients54.79Unverified
3FedSAM + SWAACC@1-100Clients53.67Unverified
4FedSAMACC@1-100Clients53.39Unverified
5FedAvgACC@1-100Clients50.25Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAMACC@1-100Clients54.5Unverified
2FedSAM + SWAACC@1-100Clients54.36Unverified
3FedASAM + SWAACC@1-100Clients54.1Unverified
4FedSAMACC@1-100Clients53.97Unverified
5FedAvgACC@1-100Clients50.66Unverified
#ModelMetricClaimedVerifiedStatus
1FedASAMACC@1-100Clients54.81Unverified
2FedSAMACC@1-100Clients54.01Unverified
3FedSAM + SWAACC@1-100Clients53.9Unverified
4FedASAM + SWAACC@1-100Clients53.86Unverified
5FedAvgACC@1-100Clients49.92Unverified
#ModelMetricClaimedVerifiedStatus
1AdaBestAverage Top-1 Accuracy56.2Unverified