AI Paper Atlas

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

Delayed Feedback Modeling with Influence Functions

Chenlu Ding, Jiancan Wu, Yancheng Yuan, Cunchun Li, Xiang Wang, Dingxian Wang, Frank Yang, Andrew Rabinovich

AAAI 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 4 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
apply influence-function parameter update for delayed conversions to the Vanilla modelVanilla MLP · Criteo offlineAUC: 0.8353 -> 0.8411Improved
apply influence-function updateVanilla DCNV2 · Criteo offlineAUC: 0.8370 -> 0.8410Improved
apply influence-function update vs FSIW (best baseline)MLP · Criteo offlineLog loss: 0.4020 -> 0.3958Improved
use IF-DFM instead of ULC at larger gap c=14MLP · Criteo offline c=14AUC: 0.8345 -> 0.8420Improved
longer time gap c=14 for ULC and DFMULC/DFM · Criteo offlineAUC: Vanilla 0.8369 vs ULC 0.8345, DFM 0.8351Hurt
use nnDF with global informationnnDF · Criteo offlineAUC: 0.8353 (Vanilla) -> 0.6887Hurt
add newly arrived data update (delta theta add) to delay-only update (ablation)IF-DFM online · Criteo onlineAUC, PRAUC: +0.36% AUC, +0.47% PRAUCImproved
use influence function update instead of retrainingIF-DFM · Criteo offline c=10running time (s): 1351.4 -> 14.8Improved
use ULC auxiliary label correction modelULC · Criteo offline c=10running time (s): 1351.4 -> 2467.4Hurt

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