AI Paper Atlas

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

Curriculum Disentangled Recommendation with Noisy Multi-feedback

Hong Chen, Yudong Chen, Xin Wang, Ruobing Xie, Rui Wang, Feng Xia, Wenwu Zhu

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 31 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 adjustable self-evaluating curriculum (ablation)CDR · Amazon-BeautyAUC: 0.7914 -> 0.7991Improved
add adjustable self-evaluating curriculum (ablation)CDR · Amazon-SportsAUC: 0.8083 -> 0.8152Improved
add adjustable self-evaluating curriculum (ablation)CDR · MovieLens-1MAUC: 0.8972 -> 0.9065Improved
add adjustable self-evaluating curriculum (ablation)CDR · WeChat5DAUC: 0.7548 -> 0.7622Improved
add raw unclick history without co-filtering (ablation)CDR click-only · Amazon-BeautyAUC: 0.7477 -> 0.7477No clear effect
add raw unclick history without co-filtering (ablation)CDR click-only · Amazon-SportsAUC: 0.8006 -> 0.7969Hurt
add raw unclick history without co-filtering (ablation)CDR click-only · MovieLens-1MAUC: 0.8879 -> 0.8854Hurt
add raw unclick history without co-filtering (ablation)CDR click-only · WeChat5DAUC: 0.7347 -> 0.7340Hurt
add co-filtering dynamic routing to click+unclick history (ablation)CDR c&un · Amazon-BeautyAUC: 0.7477 -> 0.7914Improved
add co-filtering dynamic routing to click+unclick history (ablation)CDR c&un · WeChat5DAUC: 0.7340 -> 0.7548Improved
set curriculum speed tau=1.0 (no decay) (ablation)CDR curriculum · Amazon-SportsAUC: 0.8152 -> 0.5645Hurt
curriculum difficulty thre=1.0 (focus on hardest samples) (ablation)CDR curriculum · Amazon-Sports/BeautyAUCHurt

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