Research map / Federated learning and privacy / Personalized and heterogeneous FL
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Timothy Castiglia, Yi Zhou, Shiqiang Wang, Swanand Kadhe, Nathalie Baracaldo, Stacy Patterson
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 embedding component selection stage (LESS-VFL vs. local lasso) (ablation) | LESS-VFL · Table 2 communication cost, MIMIC/Activity/Phishing/Gina | communication cost to reach target accuracy and spurious removal: e.g., Phishing 8.10 -> 3.99 MB; Activity 26.56 -> 21.17 MB | Improved |
| LESS-VFL instead of group lasso applied directly to VFL | feature selection in VFL · Table 2 communication cost across five datasets | communication cost (MB): Phishing 95.22 -> 3.99 MB (~20x lower) | Improved |
| LESS-VFL with heterogeneous (uneven) Gaussian noise distribution across parties | LESS-VFL · Table 3 Sylva and Gina | communication cost (MB): Sylva 5.62 both; local lasso ties LESS-VFL | No clear effect |
| add embedding component selection (LESS-VFL vs local lasso) under uneven feature partitions (ablation) | LESS-VFL · Table 3 MIMIC-III and Sylva | communication cost (MB): MIMIC-III 7.17 both; Sylva 5.62 both | No clear effect |
| LESS-VFL vs. group lasso under uneven feature partitions | LESS-VFL · Table 3 Activity | communication cost (MB): 187.39 -> 15.76 MB | Improved |
Closest papers by meaning
- FedCS: Coreset Selection for Federated Learning (CVPR 2025 · similarity 0.88)
- Vertical Federated Learning with Missing Features During Training and Inference (ICLR 2025 · similarity 0.87)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.86)
- On the Necessity of Collaboration for Online Model Selection with Decentralized Data (NeurIPS 2024 · similarity 0.86)
- Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions (ICML 2025 · similarity 0.86)
- Federated Causally Invariant Feature Learning (AAAI 2025 · similarity 0.86)
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.
