AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation

Jiankai Sun, Bortik Bandyopadhyay, Armin Bashizade, Jiongqian Liang, P. Sadayappan, Srinivasan Parthasarathy

AAAI 2019 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 45 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
Combine graph hierarchy and reachability in ATP's objective matrix and factorize it with NMF rather than SVDDirected graph embedding · Link prediction, four datasetsAUC: ATP improves over SVDM by $22.01\%$ among all datasetsImproved
Use the ATP hierarchy-and-reachability matrix instead of HOPE's higher-order proximity matricesDirected graph embedding · Link prediction, four datasetsAUC: ATP improves over HOPE-KI from $19.84\%$ to $51.97\%Improved
Use a nonlinear log transformation instead of the constant adjacency matrix (ablation)ATP · Link prediction, four datasetsAUC: ATP-log improves over ATP-Constant by $8.51\%$ in average among all datasetsImproved
Use a nonlinear log transformation instead of a linear transformation (ablation)ATP · GNUAUC: ATP-log improves over ATP-Linear by $4.74\%$ on the largest dataset GNUImproved
Use harmonic transformation instead of log transformation (ablation)ATP · Link prediction, four datasetsAUCNo clear effect
Use graph reachability from transitive closure rather than first-order neighbors alone (ablation)Hierarchy-based embedding · Cit-HepPHAUC: SA-linear improves over SA-linear-Adj by $3.1\%$ on Cit-HepPHImproved
Apply log transformation rather than linear transformation (ablation)Hierarchy-and-reachability embedding · GNUAUC: SA-log-Adj improves over SA-linear-Adj by $4.31\%$ on GNUImproved
Use ATP for question difficulty estimation rather than TrueSkillQuestion difficulty estimation · Five Stack Exchange sitesPairwise accuracy: ATP improves over TrueSkill ... on average by $6.56\%Improved
Use ATP for question difficulty estimation rather than Number-of-AnswersQuestion difficulty estimation · Five Stack Exchange sitesPairwise accuracy: ATP improves over ... Number-of-Answer ... on average by $5.92\%Improved
Use ATP for question difficulty estimation rather than QDEEQuestion difficulty estimation · Five Stack Exchange sitesPairwise accuracy: ATP improves over ... QDEE on average by $5.06\%Improved
Use ATP for cold question routing rather than ColdRouteCold question routing · Five Stack Exchange sitesAccuracy: ATP improves upon routing metric Accuracy over ColdRoute by $6.14\%Improved
Use ATP for cold question routing rather than QDEECold question routing · Five Stack Exchange sitesMRR: ATP improves upon routing metric MRR over QDEE by $7.59\%Improved

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