Research map / Federated learning and privacy / Personalized and heterogeneous FL
Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
Kihun Hong, Sejun Park, Ganguk Hwang
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 |
|---|---|---|---|
| use FALSE-VFL instead of the strongest baseline | VFL under missing alignment · 168 configurations (4 datasets, 6 train, 7 test patterns) | accuracy: +9.1 pp average; better in 160 of 168 | Improved |
| increase test-time missingness from MCAR 0 to MNAR 9 | FALSE-VFL advantage · per test mechanism | accuracy gap (pp): 1.8 -> 13.1 | Improved |
| train under higher MCAR missing rate (MCAR 5 vs MCAR 2) (ablation) | FALSE-VFL · MCAR 2 vs MCAR 5 training | accuracy ratio | Improved |
| increase number of parties K from 4 to 12 (ablation) | FALSE-VFL · Isolet, HAPT, FashionMNIST (MCAR 2, MNAR 7) | accuracy | Improved |
| increase number of parties K from 4 to 12 (ablation) | Vanilla VFL and FedHSSL · MCAR 2 | accuracy | Hurt |
| increase number of parties K from 4 to 12 (ablation) | LASER-VFL · Isolet, HAPT, FashionMNIST | accuracy | Hurt |
| increase data heterogeneity (smaller Dirichlet alpha, from infinity to 0.1) (ablation) | FALSE-VFL · 8-party Dirichlet missingness | accuracy | No clear effect |
| increase data heterogeneity (smaller Dirichlet alpha) (ablation) | LASER-VFL · 8-party Dirichlet missingness | accuracy | Improved |
| increase data heterogeneity (smaller Dirichlet alpha) (ablation) | Vanilla VFL and FedHSSL · 8-party Dirichlet missingness | accuracy | Hurt |
| use MAR assumption (FALSE-VFL-I) instead of explicit MNAR mask model (FALSE-VFL-II) (ablation) | FALSE-VFL · six train/seven test patterns | accuracy | No clear effect |
Closest papers by meaning
- Vertical Federated Learning with Missing Features During Training and Inference (ICLR 2025 · similarity 0.90)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.86)
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization (ICLR 2024 · similarity 0.86)
- VFLAIR: A Research Library and Benchmark for Vertical Federated Learning (ICLR 2024 · similarity 0.86)
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.86)
- Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions (ICML 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.
