AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning

Xumeng Gong, Cheng Yang, Chuan Shi

AAAI 2023 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis · 75 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 asymmetric strategy to the base model (ablation)Base Model · six node-classification benchmarksaverage accuracy: 85.42Improved
add random strategy to the base model (ablation)Base Model · six node-classification benchmarksaverage accuracy: 85.19Improved
add shuffling strategy to the base model (ablation)Base Model · six node-classification benchmarksaverage accuracy: 85.02Improved
add asymmetric strategy (ablation)MA-GCL · six node-classification benchmarksaverage accuracy: 85.49 -> 86.20Improved
add random strategy (ablation)MA-GCL · six node-classification benchmarksaverage accuracy: 85.83 -> 86.20Improved
add shuffling strategy (ablation)MA-GCL · six node-classification benchmarksaverage accuracy: 85.73 -> 86.20Improved
use MA-GCL rather than CCA-SSGnode classification · Coraaccuracy: 83.9 ± 0.4 -> 83.3 ± 0.4Hurt
use MA-GCL rather than CCA-SSGnode classification · CiteSeeraccuracy: 73.1 ± 0.3 -> 73.6 ± 0.1Improved
use MA-GCL rather than CCA-SSGnode classification · PubMedaccuracy: 81.3 ± 0.4 -> 83.5 ± 0.4Improved
use MA-GCL rather than SimGRACEnode classification · Coauthor-CSaccuracy: 93.45 ± 0.4 -> 94.19 ± 0.1Improved
use MA-GCL rather than CCA-SSGnode classification · Amazon-Computersaccuracy: 88.42 ± 0.3 -> 88.83 ± 0.3Improved
use MA-GCL rather than BGRLnode classification · Amazon-Photoaccuracy: 92.57 ± 0.3 -> 93.80 ± 0.1Improved

Later papers that compared with this method

1 later accepted paper reports MA-GCL as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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