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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 651–675 of 6771 papers

Title	Date	Tasks	Status	Hype
Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity	May 2, 2021	Federated LearningPersonalized Federated Learning	CodeCode Available	1
FedProto: Federated Prototype Learning across Heterogeneous Clients	May 1, 2021	Federated Learning	CodeCode Available	1
Federated Learning with Fair Averaging	Apr 30, 2021	FairnessFederated Learning	CodeCode Available	1
PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments	Apr 29, 2021	CPUFederated Learning	CodeCode Available	1
End-to-End Speech Recognition from Federated Acoustic Models	Apr 29, 2021	2k4k	CodeCode Available	1
Federated Learning for Malware Detection in IoT Devices	Apr 15, 2021	Federated LearningMalware Detection	CodeCode Available	1
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks	Apr 14, 2021	Federated LearningGraph Neural Network	CodeCode Available	1
Practical Defences Against Model Inversion Attacks for Split Neural Networks	Apr 12, 2021	Federated Learning	CodeCode Available	1
PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN	Apr 1, 2021	Federated LearningVertical Federated Learning	CodeCode Available	1
Model-Contrastive Federated Learning	Mar 30, 2021	Contrastive LearningFederated Learning	CodeCode Available	1
Federated Learning with Taskonomy for Non-IID Data	Mar 29, 2021	FairnessFederated Learning	CodeCode Available	1
A Framework for Energy and Carbon Footprint Analysis of Distributed and Federated Edge Learning	Mar 18, 2021	Federated Learning	CodeCode Available	1
A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources	Mar 10, 2021	Federated Learning	CodeCode Available	1
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space	Mar 10, 2021	Domain GeneralizationFederated Learning	CodeCode Available	1
Personalized Federated Learning using Hypernetworks	Mar 8, 2021	Federated LearningPersonalized Federated Learning	CodeCode Available	1
Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles	Mar 5, 2021	Federated LearningKnowledge Distillation	CodeCode Available	1
FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization	Mar 5, 2021	Federated Learning	CodeCode Available	1
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices	Mar 4, 2021	Distributed OptimizationFederated Learning	CodeCode Available	1
Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things	Mar 3, 2021	BIG-bench Machine LearningFederated Learning	CodeCode Available	1
Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning	Mar 3, 2021	Federated LearningImage Reconstruction	CodeCode Available	1
PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization	Mar 2, 2021	Federated LearningPrivacy Preserving	CodeCode Available	1
Heterogeneity for the Win: One-Shot Federated Clustering	Mar 1, 2021	ClusteringFederated Learning	CodeCode Available	1
Scalable federated machine learning with FEDn	Feb 27, 2021	BIG-bench Machine LearningFederated Learning	CodeCode Available	1
Practical and Private (Deep) Learning without Sampling or Shuffling	Feb 26, 2021	Deep LearningFederated Learning	CodeCode Available	1
Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach	Feb 24, 2021	Federated LearningGenerative Adversarial Network	CodeCode Available	1

Show:10 25 50

← PrevPage 27 of 271Next →

All datasets Cityscapes heterogeneous Landmarks-User-160k CIFAR-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

#	Model	Metric	Claimed	Verified	Status
1	SiloBN + ASAM	mIoU	49.75	—	Unverified
2	SiloBN + SAM	mIoU	49.1	—	Unverified
3	SiloBN	mIoU	45.96	—	Unverified
4	FedSAM + SWA	mIoU	43.42	—	Unverified
5	FedASAM + SWA	mIoU	43.02	—	Unverified
6	FedAvg + SWA	mIoU	42.48	—	Unverified
7	FedASAM	mIoU	42.27	—	Unverified
8	FedSAM	mIoU	41.22	—	Unverified
9	FedAvg	mIoU	38.65	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	Acc@1-1262Clients	68.32	—	Unverified
2	FedSAM + SWA	Acc@1-1262Clients	68.12	—	Unverified
3	FedAvg + SWA	Acc@1-1262Clients	67.52	—	Unverified
4	FedASAM	Acc@1-1262Clients	64.23	—	Unverified
5	FedSAM	Acc@1-1262Clients	63.72	—	Unverified
6	FedAvg	Acc@1-1262Clients	61.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	42.64	—	Unverified
2	FedASAM	ACC@1-100Clients	39.76	—	Unverified
3	FedSAM + SWA	ACC@1-100Clients	39.51	—	Unverified
4	FedSAM	ACC@1-100Clients	36.93	—	Unverified
5	FedAvg	ACC@1-100Clients	36.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	41.62	—	Unverified
2	FedASAM	ACC@1-100Clients	40.81	—	Unverified
3	FedSAM + SWA	ACC@1-100Clients	39.24	—	Unverified
4	FedAvg	ACC@1-100Clients	38.59	—	Unverified
5	FedSAM	ACC@1-100Clients	38.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	48.72	—	Unverified
2	FedSAM + SWA	ACC@1-100Clients	46.76	—	Unverified
3	FedASAM	ACC@1-100Clients	46.58	—	Unverified
4	FedSAM	ACC@1-100Clients	44.84	—	Unverified
5	FedAvg	ACC@1-100Clients	41.27	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	48.27	—	Unverified
2	FedASAM	ACC@1-100Clients	47.78	—	Unverified
3	FedSAM + SWA	ACC@1-100Clients	46.47	—	Unverified
4	FedSAM	ACC@1-100Clients	46.05	—	Unverified
5	FedAvg	ACC@1-100Clients	42.17	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	49.17	—	Unverified
2	FedSAM + SWA	ACC@1-100Clients	47.96	—	Unverified
3	FedASAM	ACC@1-100Clients	45.61	—	Unverified
4	FedSAM	ACC@1-100Clients	44.73	—	Unverified
5	FedAvg	ACC@1-100Clients	40.43	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM + SWA	ACC@1-100Clients	42.01	—	Unverified
2	FedSAM + SWA	ACC@1-100Clients	39.3	—	Unverified
3	FedASAM	ACC@1-100Clients	36.04	—	Unverified
4	FedSAM	ACC@1-100Clients	31.04	—	Unverified
5	FedAvg	ACC@1-100Clients	30.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM	ACC@1-100Clients	54.97	—	Unverified
2	FedASAM + SWA	ACC@1-100Clients	54.79	—	Unverified
3	FedSAM + SWA	ACC@1-100Clients	53.67	—	Unverified
4	FedSAM	ACC@1-100Clients	53.39	—	Unverified
5	FedAvg	ACC@1-100Clients	50.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM	ACC@1-100Clients	54.5	—	Unverified
2	FedSAM + SWA	ACC@1-100Clients	54.36	—	Unverified
3	FedASAM + SWA	ACC@1-100Clients	54.1	—	Unverified
4	FedSAM	ACC@1-100Clients	53.97	—	Unverified
5	FedAvg	ACC@1-100Clients	50.66	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FedASAM	ACC@1-100Clients	54.81	—	Unverified
2	FedSAM	ACC@1-100Clients	54.01	—	Unverified
3	FedSAM + SWA	ACC@1-100Clients	53.9	—	Unverified
4	FedASAM + SWA	ACC@1-100Clients	53.86	—	Unverified
5	FedAvg	ACC@1-100Clients	49.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AdaBest	Average Top-1 Accuracy	56.2	—	Unverified