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 63016350 of 6771 papers

TitleStatusHype
Dynamic Defense Against Byzantine Poisoning Attacks in Federated LearningCode1
Efficient Sparse Secure Aggregation for Federated Learning0
Group Knowledge Transfer: Federated Learning of Large CNNs at the EdgeCode1
Flower: A Friendly Federated Learning Research FrameworkCode1
Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems0
Evaluation of Federated Learning in Phishing Email Detection0
FedML: A Research Library and Benchmark for Federated Machine LearningCode2
Learning discrete distributions: user vs item-level privacy0
Fast-Convergent Federated Learning0
Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence0
Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms0
FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition0
IBM Federated Learning: an Enterprise Framework White Paper V0.1Code1
A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective0
Byzantine-Resilient Secure Federated Learning0
FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning0
Incentives for Federated Learning: a Hypothesis Elicitation Approach0
Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach0
Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog NetworksCode1
Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms0
Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge ComputingCode1
Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise0
Learn distributed GAN with Temporary DiscriminatorsCode1
Prioritized Multi-Criteria Federated Learning0
Data Poisoning Attacks Against Federated Learning SystemsCode1
Less is More: A privacy-respecting Android malware classifier using Federated LearningCode0
HyperTune: Dynamic Hyperparameter Tuning For Efficient Distribution of DNN Training Over Heterogeneous Systems0
Federated Learning in Mobile Edge Computing: An Edge-Learning Perspective for Beyond 5G0
FetchSGD: Communication-Efficient Federated Learning with Sketching0
FedBoosting: Federated Learning with Gradient Protected Boosting for Text RecognitionCode0
Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning0
Data-driven geophysics: from dictionary learning to deep learning0
Model Fusion with Kullback--Leibler DivergenceCode0
Quality Inference in Federated Learning with Secure Aggregation0
Privacy Amplification via Random Check-Ins0
VAFL: a Method of Vertical Asynchronous Federated Learning0
A Unified Linear Speedup Analysis of Federated Averaging and Nesterov FedAvg0
Data science and AI in FinTech: An overview0
Differentially private cross-silo federated learningCode1
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT ImagingCode1
Client Adaptation improves Federated Learning with Simulated Non-IID ClientsCode0
Federated Learning of User Authentication Models0
Attack of the Tails: Yes, You Really Can Backdoor Federated LearningCode1
BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning0
Self-organizing Democratized Learning: Towards Large-scale Distributed Learning SystemsCode0
Personalized Cross-Silo Federated Learning on Non-IID Data0
A Federated F-score Based Ensemble Model for Automatic Rule Extraction0
Coded Computing for Federated Learning at the Edge0
Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data0
A Distributed Cubic-Regularized Newton Method for Smooth Convex Optimization over Networks0
Show:102550
← PrevPage 127 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