CVPR 2023 accepted papers on Federated learning and privacy
28 of the 2,359 papers accepted at CVPR 2023 (1.2%) are on Federated learning and privacy, compared with 1.2% at CVPR 2022. They fall into 4 topics.
See CVPR 2023 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 · 16 papers
- Rethinking Federated Learning With Domain Shift: A Prototype View (181 citations)
- ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients (95 citations)
- Federated Domain Generalization With Generalization Adjustment (91 citations)
- DaFKD: Domain-Aware Federated Knowledge Distillation (75 citations)
- Fair Federated Medical Image Segmentation via Client Contribution Estimation (72 citations)
- FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation (70 citations)
- Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning (64 citations)
- Learning Federated Visual Prompt in Null Space for MRI Reconstruction (51 citations)
- Reliable and Interpretable Personalized Federated Learning (34 citations)
- Federated Learning With Data-Agnostic Distribution Fusion (33 citations)
- Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization (32 citations)
- Bias-Eliminating Augmentation Learning for Debiased Federated Learning (24 citations)
and 4 more in the interactive map.
Privacy attacks and secure learning · 6 papers
- DartBlur: Privacy Preservation With Detection Artifact Suppression (20 citations)
- Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack (13 citations)
- The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning (13 citations)
- STDLens: Model Hijacking-Resilient Federated Learning for Object Detection (10 citations)
- CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss (7 citations)
- Private Image Generation With Dual-Purpose Auxiliary Classifier (7 citations)
Communication-efficient FL · 4 papers
- FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning (103 citations)
- Elastic Aggregation for Federated Optimization (49 citations)
- On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data (40 citations)
- Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity (12 citations)