AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Jia-Qi Yang, De-Chuan Zhan

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 3 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
set alpha to zero (remove sample-complexity weight) (ablation)GDFM · CriteoAUC: 0.8349 -> 0.8333Hurt
set beta to zero (remove temporal weight) (ablation)GDFM · CriteoPR-AUC: 0.6311 -> 0.6314No clear effect
set lambda to zero (remove regularizer) (ablation)GDFM · CriteoNLL: 0.3960 -> 0.3988Hurt
add synthetic action informative with p=0.5GDFM · CriteoAUC: 0.8349 -> 0.835No clear effect
raise informativeness of added action from p=0.5 to p=0.95GDFM · CriteoAUC: 0.835 -> 0.840Improved
raise informativeness of added action from p=0.5 to p=0.95GDFM · CriteoNLL: 0.396 -> 0.391Improved
raise informativeness of added action from p=0.5 to p=0.95GDFM · CriteoPR-AUC: 0.631 -> 0.641Improved
use FNW instead of GDFMFNW · TaobaoNLL: -361Hurt
use ES-DFM instead of GDFMES-DFM · TaobaoNLL: -214Hurt
use MM-DFM instead of GDFMMM-DFM · CriteoPR-AUC: 68.1 -> 39.2Hurt
use Vanilla instead of GDFMVanilla · CriteoAUC: 74.9 -> 25.2Hurt
use ES-DFM instead of GDFMES-DFM · TaobaoPR-AUC: 80.7 -> 19.6Hurt

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