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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1701–1750 of 6771 papers

TitleStatusHype
Blockchain and Federated Edge Learning for Privacy-Preserving Mobile Crowdsensing—0
Diverse Client Selection for Federated Learning via Submodular Maximization—0
Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review—0
Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems—0
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing—0
DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences—0
Blockchain-Based Federated Learning: Incentivizing Data Sharing and Penalizing Dishonest Behavior—0
Data Distribution Shifts in (Industrial) Federated Learning as a Privacy Issue—0
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD—0
Do Gradient Inversion Attacks Make Federated Learning Unsafe?—0
Blockchain-based Federated Learning for Failure Detection in Industrial IoT—0
Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning—0
Domain Generalization for Cross-Receiver Radio Frequency Fingerprint Identification—0
Don't encrypt the data; just approximate the model \ Towards Secure Transaction and Fair Pricing of Training Data—0
Don't Forget What I did?: Assessing Client Contributions in Federated Learning—0
Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory—0
Data, Competition, and Digital Platforms—0
Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy—0
Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration—0
Do We Really Need to Design New Byzantine-robust Aggregation Rules?—0
Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem—0
DP^2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization—0
DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models—0
DP^2-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring—0
Adaptive Differential Privacy in Federated Learning: A Priority-Based Approach—0
DPBalance: Efficient and Fair Privacy Budget Scheduling for Federated Learning as a Service—0
DPCOVID: Privacy-Preserving Federated Covid-19 Detection—0
Blockchain-based Trustworthy Federated Learning Architecture—0
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation—0
On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates—0
DPP-based Client Selection for Federated Learning with Non-IID Data—0
DP-REC: Private & Communication-Efficient Federated Learning—0
Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge Computing—0
DPVS-Shapley:Faster and Universal Contribution Evaluation Component in Federated Learning—0
DPZV: Elevating the Tradeoff between Privacy and Utility in Zeroth-Order Vertical Federated Learning—0
DQRE-SCnet: A novel hybrid approach for selecting users in Federated Learning with Deep-Q-Reinforcement Learning based on Spectral Clustering—0
DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks—0
DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences—0
DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data—0
DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing—0
DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup—0
Drift-Aware Federated Learning: A Causal Perspective—0
Blockchain-Enabled Federated Learning: A Reference Architecture Design, Implementation, and Verification—0
An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee—0
Efficient Federated Finetuning of Tiny Transformers with Resource-Constrained Devices—0
A blockchain-orchestrated Federated Learning architecture for healthcare consortia—0
Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints—0
Dual-Criterion Model Aggregation in Federated Learning: Balancing Data Quantity and Quality—0
Blockchain-enabled Trustworthy Federated Unlearning—0
Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout—0
Show:102550
← PrevPage 35 of 136Next →
All datasetsCityscapes heterogeneousLandmarks-User-160kCIFAR-100 (alpha=0, 10 clients per round)CIFAR-100 (alpha=0, 20 clients per round)CIFAR-100 (alpha=0.5, 10 clients per round)CIFAR-100 (alpha=0.5, 20 clients per round)CIFAR-100 (alpha=0.5, 5 clients per round)CIFAR-100 (alpha=0, 5 clients per round)CIFAR-100 (alpha=1000, 10 clients per round)CIFAR-100 (alpha=1000, 20 clients per round)CIFAR-100 (alpha=1000, 5 clients per round)CIFAR100 (alpha=0.3, 10 clients per round)

Benchmark Results

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