AI Paper Atlas

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

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger

ICLR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 2 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
Aggregate candidate models using importance-weighted least squaresUnsupervised domain adaptation parameter choice · Amazon Reviews, Sleep-EDF, UCI-HAR, HHAR, WISDM, and two other datasetstarget accuracyImproved
Use importance-weighted least squares aggregation instead of IWV or DEV model selectionUnsupervised domain adaptation parameter choice · All seven datasetstarget accuracyImproved
Aggregate candidate models with IWA instead of heuristic aggregationUnsupervised domain adaptation parameter choice · Seven datasetstarget accuracyMixed
Use target majority voting, target majority voting regression, target confidence average regression, or source-only regression instead of IWV/DEVUnsupervised domain adaptation parameter choice · Seven datasetstarget accuracyImproved
Use linear aggregation rather than selecting a single candidate modelCandidate models for unsupervised domain adaptation · UCI-HARtarget accuracy: 0.850 -> 0.835Hurt
Use linear aggregation rather than selecting a single candidate modelCandidate models for unsupervised domain adaptation · HHARtarget accuracy: 0.784 -> 0.787Improved
Use linear aggregation rather than selecting a single candidate modelCandidate models for unsupervised domain adaptation · Amazon Reviewstarget accuracy: 0.781 -> 0.788No clear effect
Use linear aggregation rather than selecting a single candidate modelCandidate models for unsupervised domain adaptation · Sleep-EDFtarget accuracy: 0.712 -> 0.737Improved
Use linear aggregation rather than selecting a single candidate modelCandidate models for unsupervised domain adaptation · WISDMtarget accuracy: 0.771 -> 0.764Hurt

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