AI Paper Atlas

Research map / Graph learning / GNN architectures

Neural Approximation of Graph Topological Features

Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Yusu Wang, Chao Chen

NeurIPS 2022 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 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
predict EPD instead of persistence image directly (GAT vs GAT_PI) (ablation)GAT · Cora vicinity graphsPIE: 1.43e-1 -> 2.46e-2Improved
add min aggregation AGG (GAT vs GAT (+MIN)) (ablation)GAT · Cora vicinity graphsW2 distance: 0.655 -> 0.579Improved
add new edge-feature MSG function (GAT (+MIN) to PDGNN) (ablation)GAT (+MIN) · Cora vicinity graphsW2 distance: 0.579 -> 0.241Improved
remove edge weights from PDGNN (ablation)PDGNN · Computers vicinity graphsW2 distance: 0.220 -> 18.63Hurt
replace true EPD with PDGNN-approximated EPD in PEGNPEGN · Cora node classificationaccuracy: 82.7 -> 82.0No clear effect
replace true EPD with GIN_PI-predicted persistence image in PEGNPEGN · Citeseer node classificationaccuracy: 71.9 -> 65.7Hurt
replace true EPD with GIN_PI in TLC-GNNTLC-GNN · Photo link predictionAUC-ROC: 98.2 -> 95.8Hurt
replace true EPD with PDGNN EPD in TLC-GNNTLC-GNN · Photo link predictionAUC-ROC: 98.2 -> 98.4No clear effect
use PDGNN instead of Gudhi for EPD computation on large dense graphsPDGNN · Computers EPD timetime (s): 8585.50 -> 7.32Improved
use PDGNN instead of Gudhi on small graphsPDGNN · Cora EPD timetime (s): 0.44 -> 5.21Hurt
fine-tune pre-trained PDGNN for one epoch on new graphPDGNN pretrained on Photo · PubMedW2 distance: 0.444 -> 0.360Improved
increase training vicinity graphs from 5% to 80% (ablation)PDGNN · CoraW2 distance: 0.391 -> 0.241Improved

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