AI Paper Atlas

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

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

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

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 20 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
replace uniform negative sampling with sampling-free full-sample trainingCML · MovieLens-100kNDCG@5: 17.40 -> 24.65Improved
replace uniform negative sampling with sampling-free full-sample trainingCML · CiteULikeMAP: 4.67 -> 6.70Improved
replace uniform negative sampling with sampling-free full-sample trainingCML · CiteULikeAUC: 86.62 -> 83.44Hurt
replace popularity negative sampling with sampling-free trainingCML · CiteULikeNDCG@5: 9.72 -> 10.29Improved
replace popularity negative sampling with sampling-free trainingCML · MovieLens-100kNDCG@5: 13.93 -> 24.65Improved
replace hard negative sampling with sampling-free trainingCML · MovieLens-100kMAP: 15.94 -> 18.00Improved
use SFCML instead of sampling-free neural EHCFSFCML vs EHCF · CiteULikeNDCG@5: 6.29 -> 10.29Improved
use fast graph-based SFCML instead of naive full-sample CMLSFCML · CiteULikeall metricsImproved
use graph-accelerated SFCML instead of naive full-sample CMLSFCML · MovieLens-100kMAP: 17.62 -> 18.00No clear effect
replace sampling-based translation CML (CRML) with SFCMLCRML · MovieLens-100kMAP: 16.33 -> 18.00Improved

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