AI Paper Atlas

Research map / Graph learning / GNN architectures

Structural Landmarking and Interaction Modelling: A “SLIM” Network for Graph Classification

Yaokang Zhu, Kai Zhang, Jun Wang, Haibin Ling, Jie Zhang, Hongyuan Zha

AAAI 2022 · Graph learning › GNN architectures · approach: Graph structure learning · 6 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 landmark density features with landmark interaction features (ablation)SLIM · MUTAGaccuracy: 84.36 -> 93.28Improved
replace landmark density features with landmark interaction features (ablation)SLIM · PTCaccuracy: 58.94 -> 74.41Improved
replace landmark density features with landmark interaction features (ablation)SLIM · PROTEINSaccuracy: 71.25 -> 77.47Improved
replace landmark density features with landmark interaction features (ablation)SLIM · NCI1accuracy: 68.34 -> 80.53Improved
use SLIM rather than the strongest listed baselinegraph classification · MUTAGaccuracy: 92.63±4.21 -> 93.28±3.36Improved
use SLIM rather than the strongest listed baselinegraph classification · PTCaccuracy: 71.46±2.21 -> 72.41±6.92Improved
use SLIM rather than the strongest listed baselinegraph classification · NCI1accuracy: 84.46±0.45 -> 80.53±2.01Hurt
use SLIM rather than the strongest listed baselinegraph classification · Proteinaccuracy: 76.89±1.67 -> 77.47±4.34Improved
use SLIM rather than the strongest listed baselinegraph classification · D&Daccuracy: 79.72±1.98 -> 79.61±2.66Hurt
use SLIM rather than the strongest listed baselinegraph classification · IMDB-Baccuracy: 75.93±3.61 -> 77.23±2.12Improved
use SLIM rather than the strongest listed baselinegraph classification · IMDB-Maccuracy: 52.82±4.65 -> 53.38±4.02Improved
use SLIM rather than the strongest listed baselinegraph classification · COLLABaccuracy: 83.60±1.22 -> 78.22±2.02Hurt

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