CVPR 2024 accepted papers on Federated learning and privacy
37 of the 2,716 papers accepted at CVPR 2024 (1.4%) are on Federated learning and privacy, compared with 1.2% at CVPR 2023. They fall into 4 topics.
See CVPR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Personalized and heterogeneous FL · 20 papers
- FedAS: Bridging Inconsistency in Personalized Federated Learning (99 citations)
- An Aggregation-Free Federated Learning for Tackling Data Heterogeneity (61 citations)
- Relaxed Contrastive Learning for Federated Learning (43 citations)
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (40 citations)
- FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning (38 citations)
- Global and Local Prompts Cooperation via Optimal Transport for Federated Learning (37 citations)
- Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts (35 citations)
- An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning (30 citations)
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (23 citations)
- PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees (20 citations)
- FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning (19 citations)
- Traceable Federated Continual Learning (19 citations)
and 8 more in the interactive map.
Privacy attacks and secure learning · 9 papers
- Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space (43 citations)
- Privacy-Preserving Face Recognition Using Trainable Feature Subtraction (33 citations)
- Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping (28 citations)
- A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning (21 citations)
- Data Valuation and Detections in Federated Learning (15 citations)
- Privacy-Preserving Optics for Enhancing Protection in Face De-Identification (14 citations)
- Validating Privacy-Preserving Face Recognition under a Minimum Assumption (10 citations)
- Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning (7 citations)
- All Rivers Run to the Sea: Private Learning with Asymmetric Flows (1 citation)
Communication-efficient FL · 7 papers
- Communication-Efficient Federated Learning with Accelerated Client Gradient (38 citations)
- Decentralized Directed Collaboration for Personalized Federated Learning (31 citations)
- Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices (23 citations)
- FedMef: Towards Memory-efficient Federated Dynamic Pruning (20 citations)
- Federated Online Adaptation for Deep Stereo (16 citations)
- Device-Wise Federated Network Pruning (8 citations)
- DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models (3 citations)