AI Paper Atlas

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

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use FALSE-VFL instead of the strongest baselineVFL under missing alignment · 168 configurations (4 datasets, 6 train, 7 test patterns)accuracy: +9.1 pp average; better in 160 of 168Improved
increase test-time missingness from MCAR 0 to MNAR 9FALSE-VFL advantage · per test mechanismaccuracy gap (pp): 1.8 -> 13.1Improved
train under higher MCAR missing rate (MCAR 5 vs MCAR 2) (ablation)FALSE-VFL · MCAR 2 vs MCAR 5 trainingaccuracy ratioImproved
increase number of parties K from 4 to 12 (ablation)FALSE-VFL · Isolet, HAPT, FashionMNIST (MCAR 2, MNAR 7)accuracyImproved
increase number of parties K from 4 to 12 (ablation)Vanilla VFL and FedHSSL · MCAR 2accuracyHurt
increase number of parties K from 4 to 12 (ablation)LASER-VFL · Isolet, HAPT, FashionMNISTaccuracyHurt
increase data heterogeneity (smaller Dirichlet alpha, from infinity to 0.1) (ablation)FALSE-VFL · 8-party Dirichlet missingnessaccuracyNo clear effect
increase data heterogeneity (smaller Dirichlet alpha) (ablation)LASER-VFL · 8-party Dirichlet missingnessaccuracyImproved
increase data heterogeneity (smaller Dirichlet alpha) (ablation)Vanilla VFL and FedHSSL · 8-party Dirichlet missingnessaccuracyHurt
use MAR assumption (FALSE-VFL-I) instead of explicit MNAR mask model (FALSE-VFL-II) (ablation)FALSE-VFL · six train/seven test patternsaccuracyNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy