AI Paper Atlas

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

Large-Scale Heterogeneous Feature Embedding

Xiao Huang, Qingquan Song, Fan Yang, Xia Hu

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 27 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 network G to feature matrix X (FeatWalk vs FeatWalk X) (ablation)FeatWalk · Flickr, 100% trainingmicro-average: 0.868 -> 0.893Improved
add network G to feature matrix X (FeatWalk vs FeatWalk X) (ablation)FeatWalk · ACM, 100% trainingmicro-average: 0.667 -> 0.751Improved
add network G to feature matrix X (FeatWalk vs FeatWalk X) (ablation)FeatWalk · Yelp, 100% trainingmicro-average: 0.699 -> 0.701No clear effect
add second feature matrix X(2) (Spanish) to X(1) (Italian) (ablation)FeatWalk · Reuters, 100% trainingmicro-average: 0.744 -> 0.771Improved
use Feature Walks instead of explicit similarity-matrix random walks (w/o FW) (ablation)FeatWalk · ACM, Yelprunning timeImproved
add features to network embedding (FeatWalk vs DeepWalk)DeepWalk · ACM, 100% trainingmicro-average: 0.684 -> 0.751Improved
FeatWalk vs AANEAANE · Flickr, 100% trainingmicro-average: 0.885 -> 0.893Improved
FeatWalk vs AANEAANE · Yelp, 100% trainingmicro-average: 0.714 -> 0.701Hurt
add multi-threading workers (1 to 2) (ablation)FeatWalk · all datasetsrunning timeImproved
vary embedding dimension d from 20 to 180 (ablation)FeatWalk · Flickrmicro-averageNo clear effect
vary window size 1 to 10 (ablation)FeatWalk · Flickrmicro-averageNo clear effect
balance feature and network weight alpha (0.62 vs 0 or 1) (ablation)FeatWalk · Flickrmicro-averageImproved

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