AI Paper Atlas

Research map / Detection and segmentation / CNN features

Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism

Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, Yuan Qi

AAAI 2019 · Detection and segmentation › CNN features · approach: Forgery detection · 154 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
HACUD (meta-path neighbor features with hierarchical attention) vs GBDTStructcash-out user detection · Ant Credit Pay One MonthAUC: 0.6968 -> 0.7160Improved
add meta-path neighbor aggregate features to GBDTGBDT · Ant Credit Pay Ten DaysAUC: 0.6389 -> 0.6948Improved
add node features to structure embeddingsNode2vec · Ant Credit Pay Ten DaysAUC: 0.5913 -> 0.6464Improved
add meta-path-level attention (ablation)HACUD without path attention · Ant Credit PayAUCImproved
add feature-level attention (ablation)HACUD without path and feature attention · Ant Credit PayAUCImproved
incorporate more meta-paths (UMU, UU, UM) (ablation)HACUD · Ant Credit PayAUCImproved
vary latent dimension d from 16 to 128 (ablation)HACUD · Ant Credit Pay Ten DaysAUC: 0.7066 / 0.7115 / 0.7056 / 0.7049No clear effect

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