AI Paper Atlas

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

A Discriminative Technique for Multiple-Source Adaptation

Corinna Cortes, Mehryar Mohri, Ananda Theertha Suresh, Ningshan Zhang

ICML 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 6 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 conditional domain-membership probabilities rather than KDE density estimates for distribution-weighted source-predictor combinationMSA · Sentiment Analysis Test Data, KDBEMSE: 1.65$\pm$0.04 -> 1.59$\pm$0.04Improved
Use conditional domain-membership probabilities rather than KDE density estimates for distribution-weighted source-predictor combinationMSA · Digits Test Data, meanaccuracy: 94.7 -> 95.4Improved
Use conditional domain-membership probabilities rather than KDE density estimates for distribution-weighted source-predictor combinationMSA · Adult, NDocaccuracy: 76.4 $\pm$ 1.6 -> 80.5 $\pm$ 0.5Improved
Use conditional domain-membership probabilities rather than KDE density estimates for distribution-weighted source-predictor combinationMSA · Adult, Docaccuracy: 70.2 $\pm$ 1.2 -> 70.0 $\pm$ 0.8No clear effect
Use conditional domain-membership probabilities rather than KDE density estimates for distribution-weighted source-predictor combinationMSA · Adult, Doc-NDocaccuracy: 73.3 $\pm$ 0.8 -> 75.3 $\pm$ 0.4Improved

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