AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning

Robin Winter, Frank Noe, Djork-Arne Clevert

NeurIPS 2021 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 2 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
use PIGAE instead of GAE for graph reconstructionGraph autoencoding · Erdos-Renyi, Barabasi-Albert, and Ego graphsNLL: 20.5 ± 0.9 vs 186 ± 3; 27.2 ± 0.9 vs 199 ± 3; 23.4 ± 0.5 vs 191 ± 4Improved
use PIGAE instead of GAE for graph reconstructionGraph autoencoding · Erdos-Renyi, Barabasi-Albert, and Ego graphsROC-AUC: 98.3 ± 0.1 vs 57.9 ± 0.1; 96.7 ± 0.2 vs 57.4 ± 0.1; 97.8 ± 0.3 vs 59.1 ± 0.1Improved
use PIGAE instead of GraphiteGraph reconstruction · Erdos-Renyi, Barabasi-Albert, and Ego graphsNLL: 20.5 ± 0.9 vs 196 ± 1; 27.2 ± 0.9 vs 192 ± 2; 23.4 ± 0.5 vs 183 ± 1Improved
use PIGAE instead of GAE*Graph reconstruction · Erdos-Renyi, Barabasi-Albert, and Ego graphsNLL: 20.5 ± 0.9 vs 222 ± 8; 27.2 ± 0.9 vs 236 ± 15; 23.4 ± 0.5 vs 197 ± 2Improved
add topological distances as edge features (ablation)PIGAE · Erdos-Renyi, Barabasi-Albert, and Ego graphsNLL: 20.5 ± 0.9 -> 19.5 ± 0.8; 27.2 ± 0.9 -> 15.2 ± 0.8; 23.4 ± 0.5 -> 22.4 ± 0.5Improved
add topological distances as edge features (ablation)PIGAE · Erdos-Renyi, Barabasi-Albert, and Ego graphsROC-AUC: 98.3 ± 0.1 -> 99.4 ± 0.1; 96.7 ± 0.2 -> 99.5 ± 0.1 ; 97.8 ± 0.3 -> 98.8 ± 0.3Improved
use PIGAE representations instead of averaged GAE node embeddingsSVM graph-class prediction · Synthetic graph class prediction (29 classes)accuracy: 0.65 ± 0.01 -> 0.83 ± 0.01Improved
use PIGAE representations instead of InfoGraph representationsSVM graph-class prediction · Synthetic graph class prediction (29 classes)accuracy: 0.75 ± 0.02 -> 0.83 ± 0.01Improved
use PIGAE representations instead of Shortest Path KernelSVM graph-class prediction · Synthetic graph class prediction (29 classes)accuracy: 0.50 ± 0.02 -> 0.83 ± 0.01Improved
use PIGAE representations instead of Weisfeiler-Lehman Sub-tree KernelSVM graph-class prediction · Synthetic graph class prediction (29 classes)accuracy: 0.73 ± 0.01 -> 0.83 ± 0.01Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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