Research map / Federated learning and privacy / Personalized and heterogeneous FL
Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification
Ziyuan Yang, Andrew Beng Jin Teoh, Bob Zhang, Lu Leng, Yi Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add anchor proximal loss to global proximal loss (ablation) | PSFed-Palm · PolyU Multi-Spectral | EER (%): 0.01009 -> 0.00886 | Improved |
| add MSE loss to global proximal loss (ablation) | PSFed-Palm · PolyU Multi-Spectral | EER (%): 0.01009 -> 0.00828 | Improved |
| add MSE loss to global and anchor proximal losses (ablation) | PSFed-Palm · PolyU Multi-Spectral | EER (%): 0.00886 -> 0.00678 | Improved |
| add anchor proximal loss to global proximal + MSE (ablation) | PSFed-Palm · PolyU Multi-Spectral | EER (%): 0.00828 -> 0.00678 | Improved |
| add global proximal loss to anchor proximal + MSE (ablation) | PSFed-Palm · PolyU Multi-Spectral | EER (%): 0.01190 -> 0.00678 | Improved |
| use FedProx proximal term instead of FedAvg | FedAvg · PolyU Multi-Spectral | EER (%): 0.06170 -> 0.05147 | Improved |
| use PSFed-Palm instead of FedAvg | FedAvg · PolyU Multi-Spectral | EER (%): 0.06170 -> 0.03556 | Improved |
| use federated learning instead of independent training | w/o FL · PolyU Multi-Spectral | EER (%): 0.06731 -> 0.06170 | Improved |
| use personalized layers (FedPer) instead of FedAvg | FedAvg · PolyU Multi-Spectral | EER (%): 0.06170 -> 1.40338 | Hurt |
| personalize batch norm (FedBN) instead of FedAvg | FedAvg · PolyU Multi-Spectral | EER (%): 0.06170 -> 0.16751 | Hurt |
| use PSFed-Palm with larger CO3Net base model | FedAvg · PolyU Multi-Spectral (CO3Net) | EER (%): 0.01407 -> 0.00868 | Improved |
| use PSFed-Palm on CASIA Multi-Spectral | FedAvg · CASIA Multi-Spectral | EER (%): 1.60464 -> 1.22485 | Improved |
Closest papers by meaning
- Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models (CVPR 2025 · similarity 0.85)
- PCE-Palm: Palm Crease Energy Based Two-Stage Realistic Pseudo-Palmprint Generation (AAAI 2024 · similarity 0.83)
- PVTree: Realistic and Controllable Palm Vein Generation for Recognition Tasks (AAAI 2025 · similarity 0.81)
- Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication (AAAI 2024 · similarity 0.80)
- OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting (AAAI 2025 · similarity 0.80)
- FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data (ICML 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
