AI Paper Atlas

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

Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings

Lotta Mäkinen, Jorge Loria, Samuel Kaski

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 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
condition prior on ICP causal embeddings (expert-inferred) vs no transferhierarchical Bayesian meta-learner · UK Biobank J44AUROC: 0.791 -> 0.820Improved
condition prior on ICP causal embeddings (expert-inferred) vs no transferhierarchical Bayesian meta-learner · UK Biobank J45AUROC: 0.587 -> 0.620Improved
use expert-inferred ICP embeddings vs HBM global priorHBM · UK Biobank I21AUROC: 0.701 -> 0.693Hurt
replace expert-inferred with oracle ICP embeddings (ablation)ICP embeddings · UK Biobank I21AUROC: 0.693 -> 0.714Improved
replace expert-inferred with oracle ICP embeddings (ablation)ICP embeddings · UK Biobank J44AUROC: 0.820 -> 0.816No clear effect
replace expert-inferred with oracle CHI2 embeddings (ablation)CHI2 embeddings · UK Biobank J44AUROC: 0.730 -> 0.815Improved
replace expert-inferred with oracle MR embeddings (ablation)MR embeddings · UK Biobank J44AUROC: 0.805 -> 0.766Hurt
use ICP oracle embeddings instead of MR oracle (ablation)MR embeddings (oracle) · UK Biobank G45AUROC: 0.651 -> 0.673Improved
add standard meta-learning transfer (MAML) vs no transferno-transfer baseline · UK Biobank J45AUROC: 0.587 -> 0.612Improved
add DKT transfer vs no transferno-transfer baseline · UK Biobank I21AUROC: 0.704 -> 0.695No clear effect
condition prior on causal embeddings instead of global prior or correlation embeddings under increasing task shift (ablation)global-prior Bayesian meta-learner · synthetic Experiment 1AUROC under task shiftImproved
use correlation-based embeddings at in-distribution shift (ablation)global prior · synthetic Experiment 1 (eps_OOD=0.5)AUROCImproved

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