Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Data and Feature Selection by Generalized CUR Decomposition
Ying-Peng Tang, Zhuang Qi, Xiaoli Tang, Wei Zhuo, Sheng-Jun Huang, Han Yu
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 per-silo local row selection on top of FedCPQR (FedGCUR vs FedCPQR) on whole-matrix reconstruction | FedCPQR · vision benchmarks, IID split, k=1500 | Frobenius reconstruction error: CIFAR-10 WRE 30.9 -> 30.7 | Improved |
| add local row selection (FedGCUR vs FedCPQR) on non-IID reconstruction of CIFAR-100 and Tiny ImageNet | FedCPQR · vision benchmarks, non-IID split | Frobenius reconstruction error: Tiny-Img WRE 44.6 -> 45.1 | Hurt |
| add local row selection (FedGCUR vs FedCPQR) on downstream accuracy | FedCPQR · vision benchmarks, non-IID split | accuracy (%): Tiny-Img 73.1 -> 65.8; C100 69.3 -> 63.0 | Hurt |
| add local row selection (FedGCUR vs FedCPQR) on downstream accuracy | FedCPQR · USPS, isolet, gina prior2 (IID, rank 100) | accuracy (%): USPS 42.2 -> 46.9; isolet 35.7 -> 37.9 | Improved |
| use FedCPQR pivot columns instead of variance-based feature selection (using all data) | federated feature selection · isolet (IID, rank 100) | accuracy (%): 24.8 -> 35.7 | Improved |
| use FedCPQR instead of centralized SciPy pivoted QR | column pivoting · six OpenML datasets, k=10/50/100 | pivot exact match: True for all; angle error on order of 1e-14 | No clear effect |
| use FedCPQR/FedGCUR rather than random or task-specific selectors on CIFAR-10 accuracy | federated selection · CIFAR-10 (IID, k=1500) | accuracy (%): 90.1 vs Coreset.Var. 90.7 | Hurt |
| use FedCPQR with half the rows vs all data baselines on mfeat-pixel | all methods · mfeat-pixel (1022) | accuracy (%): all methods 90.0±0.0 vs oracle 92.4±0.6 | No clear effect |
| FedCPQR and FedGCUR vs FedQR runtime as parties and rank grow | FedQR · mfeat-pixel, gina prior2 | runtime | Improved |
Closest papers by meaning
- Federated Causally Invariant Feature Learning (AAAI 2025 · similarity 0.87)
- Efficient Heterogeneity-Aware Federated Active Data Selection (ICML 2025 · similarity 0.85)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.85)
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization (ICLR 2024 · similarity 0.85)
- Ranking-based Client Imitation Selection for Efficient Federated Learning (ICML 2024 · similarity 0.85)
- pFedES: Generalized Proxy Feature Extractor Sharing for Model Heterogeneous Personalized Federated Learning (AAAI 2025 · similarity 0.85)
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.
