AI Paper Atlas

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

PARS: Partial-Label-Learning-inspired Recommender Systems

Shanshan Ye, Kezhi Lu, Guangquan Zhang, Jie Lu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 1 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
use PARS (no acquisition labels) instead of CVR baselines trained with 50% positive labelsPARS · YooChooseAUC: 0.6964 -> 0.9398Improved
use PARS (no acquisition labels) instead of CVR baselines trained with 50% positive labelsPARS · RetailRocketAUC: 0.5487 -> 0.9718Improved
use PARS (no acquisition labels) instead of CVR baselines trained with 50% positive labelsPARS · TaobaoAUC: 0.5626 -> 0.8953Improved
compare PARS to baselines given 100% item acquisition labelsPARS · YooChoose, RetailRocket, TaobaoAUC/HR@KMixed
reduce ratio of positive acquisition labels given to DeepFM below 10% (ablation)DeepFM · YooChoose and TaobaoAUC: decline up to 35% (YooChoose), 42% (Taobao)Hurt
PARS without labels vs DeepFM with 100% labelsPARS · RetailRocket, YooChoose, TaobaoAUC, HR@1, Recall@1, F1@1Improved

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