AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

IdeFN: Identifying Unclicked Space False Negatives via Relaxed Partial Optimal Transport for Conversion Rate Prediction

Weiyi Zhong, Weiming Liu, Lianyong Qi, Xiaoran Zhao, Xiaolong Xu, Haolong Xiang, Yang Cao, Shichao Pei, Qiang Ni

AAAI 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 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
add IdeFN false-negative relabeling to ESMMESMM (MLP) · Ali-CCPAUC: 0.6313 -> 0.6656Improved
add IdeFN to MMoEMMoE · Ali-CCPAUC: 0.6241 -> 0.6641Improved
add IdeFN to MMoEMMoE · KuaiRand-PureAUC: 0.8310 -> 0.8672Improved
add IdeFN to ESMMESMM (MLP) · KuaiRand-PureLogLoss: 0.0703 -> 0.0632Improved
IdeFN vs runner-up NISEIdeFN (MLP) · Ali-CCPAUC: 0.6515 -> 0.6656Improved
IdeFN vs runner-up NISEIdeFN (DCNV2) · KuaiRand-PureAUC: 0.8588 -> 0.8756Improved
ESCM2-DR with DCNV2 backboneESCM2-DR · KuaiRand-PureAUC: 0.8101 (DeepFM) -> 0.6442 (DCNV2)Hurt
add CTR auxiliary task (ablation)IdeFN · Ali-CCPAUC/KSImproved
add RPOT module (identify false negatives in unclicked space) (ablation)IdeFN · Ali-CCPAUC/KSImproved
increase kappa (fraction of unclicked allowed to match positives) too large (ablation)IdeFN · KuaiRand-PureAUC/KSHurt
vary CVR/CTR loss weight gamma away from 30 (ablation)IdeFN · KuaiRand-PureAUC/KSHurt
vary alpha away from 0.8 (ablation)IdeFN · KuaiRand-PureAUC/KSHurt

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