AI Paper Atlas

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

Robust Negative Sampling for Network Embedding

Mohammadreza Armandpour, Patrick Ding, Jianhua Huang, Xia Hu

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 40 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 NS with R-NS (distant negative sampling plus norm penalty)LINE · BlogCatalog, Type II, 50% labeledMicro-F1: 0.12 -> 0.25Improved
replace NS with R-NSLINE · Flickr, Type II, 50% labeledMicro-F1: 0.46 -> 0.57Improved
replace NS with R-NSLINE · Wikipedia, Type I, 50% labeledMicro-F1: 0.47 -> 0.48Improved
add the norm penalty to R-NS (lambda 0 -> formula) (ablation)R-NS · BlogCatalog, Type IIMicro-F1: 0.15 -> 0.25Improved
add the norm penalty to R-NS (ablation)R-NS · Wikipedia, Type IMicro-F1: 0.42 -> 0.48Improved
exclude neighbors from negative sampling without penalty (ablation)NS · BlogCatalog, Type IMicro-F1: 0.36 -> 0.34Hurt
use R-NS penalty formula instead of NN-NS implicit degree-based penalty (ablation)R-NS · Flickr, Type IIMicro-F1: 0.41 -> 0.57Improved
vary lambda away from formula value (ablation)R-NS · BlogCatalog and WikipediaMicro-F1Mixed

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