AI Paper Atlas

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

A Difference Standardization Method for Mutual Transfer Learning

Haoqing Xu, Meng Wang, Beilun Wang

ICML 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning

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
Standardize domain differences (divide by Sigma_i+Sigma_j)^-1/2 before l2 distance (ablation)DiffS · Synthetic (M=50, n=100, p=q=10, S=5)learnability structure NMI: 0.998 vs 0.902Improved
Use learnability-structure-aware DiffS instead of k-means with BIC tuningDiffS · Synthetic large-scale settingswall-clock time: about 50 to 1000x faster than k-means, 2 to 20x faster than MeTaGImproved
Use DiffS (tuning-free) instead of k-means with BIC for subgroup recoverySynthetic high-dimensional settings (p=q=30, 50)learnability structure NMI: 0.997 vs 0.047 (p=q=30); 0.954 vs 0.000 (p=q=50)Improved
Use DiffS instead of k-means on NOAA nClimDivmonthly temperature prediction · Real: NOAA nClimDivMSE: 82.44 vs 88.72Improved
Use DiffS instead of MeTaG on NOAA nClimDivmonthly temperature prediction · Real: NOAA nClimDivMSE and time: MeTaG MSE explodes and needs >10200 s, DiffS 82.44 in 33.79 sImproved
Use DiffS instead of k-means/MeTaG on Microarray datagene expression prediction · Real: Microarray DataMSE: 0.93 vs 0.96 (k-means) and 0.90 (MeTaG)Improved
Use DiffS instead of MeTaG on Microarray datagene expression prediction · Real: Microarray DataMSE: MeTaG 0.90 is lower than DiffS 0.93 within noiseMixed

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