AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock

TPAMI 2020 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 91 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 backtrackless grid construction (BASGCN vs BASGCN(U)) (ablation)BASGCN · MUTAGaccuracy (%): 89.70 -> 90.04Improved
add backtrackless grid construction (ablation)BASGCN · D&Daccuracy (%): 80.40 -> 81.20Improved
add backtrackless grid construction (ablation)BASGCN · RED-Baccuracy (%): 90.60 -> 91.00Improved
add backtrackless grid construction (ablation)BASGCN · COLLABaccuracy (%): 78.75 -> 79.60Improved
add backtrackless grid construction (ablation)BASGCN · IMDB-Baccuracy (%): 73.86 -> 74.00Improved
add backtrackless grid construction (ablation)BASGCN · PROTEINSaccuracy (%): 76.50 -> 76.05Hurt
add backtrackless grid construction (ablation)BASGCN · PTCaccuracy (%): 61.42 -> 60.50Hurt
add backtrackless grid construction (ablation)BASGCN · IMDB-Maccuracy (%): 50.86 -> 50.43Hurt
use BASGCN instead of JTQK graph kernelJTQK · RED-Baccuracy (%): 77.60 -> 91.00Improved
use BASGCN instead of JTQK graph kernelJTQK · MUTAGaccuracy (%): 85.50 -> 90.04Improved
use BASGCN instead of DGCNNDGCNN · COLLABaccuracy (%): 73.76 -> 79.60Improved
use BASGCN instead of DGCNNDGCNN · IMDB-Baccuracy (%): 70.03 -> 74.00Improved

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