AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label Information

Sihan Wang, Wenjie Du, Yang Wang

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification

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 evidence regression (replacing MSE) for absolute-value labels (ablation)Credible Subset Decomposition · TF-Bandgap (2-fidelity)MAE: 0.66 -> 0.57Improved
add interval-based uncertainty modulation with tau (ablation)Credible Subset Decomposition · TF-Bandgap (2-fidelity)MAE: 0.60 -> 0.57Improved
add ranking feature and rank loss (ablation)Credible Subset Decomposition · FF-Bandgap (5-fidelity)Kendall tau-b: 0.64 -> 0.70Improved
add ranking feature and rank loss (ablation)Credible Subset Decomposition · TF-Bandgap (2-fidelity)MAE: 0.58 -> 0.57Improved
add interval-based uncertainty modulation with tau (ablation)Credible Subset Decomposition · FF-Bandgap (5-fidelity)MAE: 0.55 -> 0.50Improved
use credible subset decomposition instead of best multi-fidelity baseline MFSEmulti-fidelity learning · TF-Bandgap (2-fidelity)MAE: 0.64 -> 0.57Improved
use credible subset decomposition instead of MFGNN with five fidelitiesmulti-fidelity learning · FF-Bandgap (5-fidelity)MAE: 0.56 -> 0.50Improved
add a fourth fidelity level (GLLB-SC data) to training mix (ablation)Credible Subset Decomposition · FF-Bandgap HSE/SCAN/PBE test setsMAEHurt
add more high-fidelity data to the training mix (ablation)Credible Subset Decomposition · FF-BandgapMAEImproved
reduce alpha_abs from 1.0 to 0.1 (rank weight fixed 5e-3) (ablation)Credible Subset Decomposition · TF-Bandgap (2-fidelity)MAE: 0.57 -> 0.69Hurt
increase alpha_rank from 1e-3 to 1e-1 (alpha_abs fixed 1.0) (ablation)Credible Subset Decomposition · TF-Bandgap (2-fidelity)MAE: 0.58 -> 0.68Hurt

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