AI Paper Atlas

Research map / Graph learning / GNN architectures

Probabilistic Learning on Graphs via Contextual Architectures

Davide Bacciu, Federico Errica, Alessio Micheli

JMLR 2020 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 15 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 bigram features to unigram vertex representation (ablation)CGMM · IMDB-Maccuracy: 47.36 -> 49.73Improved
add bigram features to unigram vertex representation (ablation)CGMM · COLLABaccuracy: 73.3 -> 75.50Improved
add bigram features to unigram vertex representation (ablation)CGMM · IMDB-Baccuracy: 71.07 -> 72.1Improved
add bigram features to unigram vertex representation (ablation)CGMM · NCI1accuracy: 77.02 -> 77.80Improved
add bigram features to unigram vertex representation (ablation)CGMM · D&Daccuracy: 77.35 -> 77.15No clear effect
condition each layer on all previous layers (switching parent) (ablation)CGMM · graph classification benchmarksaccuracy: 77.15 -> 77.20No clear effect
condition each layer on all previous layers (switching parent) (ablation)CGMM · COLLABaccuracy: 75.50 -> 76.06No clear effect
condition each layer on all previous layers (switching parent) (ablation)CGMM · PPIMicro F1: 60.2 -> 58.4Hurt
increase number of layers (1 to 20) (ablation)CGMM · NCI1accuracyImproved
increase number of layers (1 to 20) (ablation)CGMM · PROTEINS and D&DaccuracyHurt
deeper network with smaller hidden size instead of wider shallow network (ablation)CGMM · NCI1 validationaccuracy: size 60 -> size 45Improved
train a pool of candidate Bayesian Networks per layer and select best (ablation)CGMM · NCI1accuracyNo 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