AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Transfer learning for tensor Gaussian graphical models

Mingyang Ren, Yaoming Zhen, Junhui Wang

JMLR 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 1 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
add transfer from auxiliary sites to the tensor GGM (proposed vs Tlasso)tensor Gaussian graphical model · ADHD-200 TDC, target OHSUabsolute prediction error: 0.4960 -> 0.4179Improved
add transfer from auxiliary sites (proposed.v vs Tlasso)tensor Gaussian graphical model · ADHD-200 TDC, target WashUabsolute prediction error: 0.3962 -> 0.2939Improved
add transfer from auxiliary sites (proposed vs Tlasso)tensor Gaussian graphical model · ADHD-200 ADHD, target OHSUabsolute prediction error: 0.3503 -> 0.3072Improved
add transfer from auxiliary sites (proposed vs Tlasso)tensor Gaussian graphical model · ADHD-200 TDC, target NYUabsolute prediction error: 0.0122 -> 0.0144Hurt
add transfer from auxiliary sites (proposed vs Tlasso)tensor Gaussian graphical model · ADHD-200 ADHD, target NYUabsolute prediction error: 0.0139 -> 0.0166Hurt
use weights from both sample sizes and domain differences (proposed.v) instead of sample sizes only (ablation)transfer tensor GGM · ADHD-200 TDC, target NYUabsolute prediction error: 0.0144 -> 0.0112Improved
use weights from both sample sizes and domain differences (proposed.v) instead of sample sizes only (ablation)transfer tensor GGM · Simulation Scenario 2 (non-informative auxiliary domains)estimation errorImproved
add informative auxiliary domains (increase K)transfer tensor GGM · Simulation Scenario 1estimation errorsImproved
add transfer with model selection step when no auxiliary domain is informativetransfer tensor GGM · Simulation Scenario 2, card(A)=0estimation errorNo clear effect
add transfer learning on true negative ratetransfer tensor GGM · SimulationTNRImproved

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