AI Paper Atlas

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

Uplift Modeling from Separate Labels

Ikko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama

NeurIPS 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 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
Estimate uplift directly with the proposed min-max least-squares method instead of separately estimating four conditional expectationsUplift estimation on synthetic data · Synthetic dataAUUCImproved
Estimate uplift directly with the proposed method instead of FourLogistic or FourNNCUplift estimation on Email data · Email dataAUUCImproved
Estimate uplift directly with the proposed method instead of the neural-network baselinesUplift estimation on Jobs data · Jobs dataAUUCImproved
Estimate uplift directly with the proposed method instead of the baseline methodsUplift estimation on Criteo data · Criteo dataAUUCImproved
Use treatment policies that are closer to each otherUplift estimators on synthetic data · Synthetic dataAUUCHurt
Use the proposed method rather than FourNNC when policy differences are smallUplift estimation on synthetic data with b=1 · Synthetic dataSquared errorImproved
Use FourLogistic rather than FourNNCUplift estimation on Email data · Email dataAUUCImproved

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