AI Paper Atlas

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

Symmetric Metric Learning with Adaptive Margin for Recommendation

Mingming Li, Shuai Zhang, Fuqing Zhu, Wanhui Qian, Liangjun Zang, Jizhong Han, Songlin Hu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 65 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 user-specific adaptive margin to base (ablation)SML (CML-like base) · Instant VideoHR@5: 0.6911 -> 0.7256Improved
add user-specific adaptive margin to base (ablation)SML (CML-like base) · IMDBHR@5: 0.4593 -> 0.4617Improved
add user-specific adaptive margin to base (ablation)SML (CML-like base) · YelpHR@5: 0.5667 -> 0.5709Improved
add item-centric symmetric loss to base (ablation)SML (CML-like base) · Instant VideoHR@5: 0.6911 -> 0.7326Improved
add item-centric symmetric loss to base (ablation)SML (CML-like base) · IMDBHR@5: 0.4593 -> 0.4500Hurt
add item-specific margin on top of s+u (ablation)SML (CML-like base) · Instant VideoHR@5: 0.7347 -> 0.7309No clear effect
add item-specific margin on top of s+u (ablation)SML (CML-like base) · IMDBHR@5: 0.4608 -> 0.4827Improved
add item-specific margin on top of s+u (ablation)SML (CML-like base) · YelpHR@5: 0.5749 -> 0.5900Improved
increase lambda (item-centric loss weight) above 0.01SML · Instant Video, IMDBHR@KHurt
set adaptive margin strength gamma too large (>100)SML · Instant VideoHR@KHurt
use full SML instead of CMLSML · IMDBHR@5: 0.4593 -> 0.4827Improved

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