AI Paper Atlas

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

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

Shilong Bao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang

NeurIPS 2022 · 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
add DCRS regularization (ablation)DPCML2 · MovieLens-1mMaxDiv@20: 292.089 -> 313.086Improved
add DCRS regularization (ablation)DPCML1 · MovieLens-1mMaxDiv@20: 140.057 -> 145.615Improved
add DCRS regularization (ablation)DPCML1 · Steam-200kMaxDiv@20: 155.193 -> 179.065Improved
add DCRS regularization (ablation)DPCML2 · Steam-200kMaxDiv@20: 365.458 -> 369.876Improved
replace single user vector with multiple user representations (DPCML2 vs HarS, same hard sampling)CML · MovieLens-1mNDCG@5: 25.77 -> 26.16Improved
replace single user vector with multiple user representations (DPCML2 vs HarS)CML · Steam-200kNDCG@5: 26.63 -> 30.56Improved
replace single user vector with multiple user representations (DPCML1 vs UniS)CML · Steam-200kMaxDiv@20: 117.927 -> 179.065Improved
replace single user vector with multiple user representations (DPCML2 vs HarS)CML · MovieLens-1mMaxDiv@20: 244.078 -> 313.086Improved
use too many user vectors C with hard negative samplingDPCML2 · Steam-200kaccuracy metricsHurt
increase number of user vectors C (C>1 vs C=1)DPCML · Steam-200ktraining loss and test performanceImproved
tune diversity weight eta to about 10 (ablation)DPCML · Steam-200krecommendation metricsImproved
use both DCRS terms instead of only delta1 or delta2 (ablation)DPCML · Steam-200krecommendation metricsImproved

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