atlas

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

Hyperbolic Heterogeneous Information Network Embedding

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 124 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
hyperbolic (Poincaré) instead of Euclidean embedding space with meta-path walksmetapath2vec · MovieLens M-D link prediction, dim 2AUC: 0.6191 -> 0.8520Helped
hyperbolic instead of Euclidean embedding spacemetapath2vec · DBLP P-A link prediction, dim 25AUC: 0.8803 -> 0.9117Helped
hyperbolic instead of Euclidean embedding spacemetapath2vec · DBLP P-A network reconstruction, dim 2AUC: 0.6686 -> 0.9835Helped
add heterogeneous meta-path guided walks to hyperbolic embeddingPoincaréEmb · DBLP P-A link prediction, dim 25AUC: 0.7830 -> 0.9117Helped
hyperbolic instead of Euclidean first-order proximityLINE(1st) · link prediction, dim < 10AUCHelped
larger neighborhood size (ablation)HHNE · DBLP network reconstructionAUCHurt
vary walks per node and walk length (ablation)HHNE · DBLP network reconstructionAUCNo 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