AI Paper Atlas

Research map / Graph learning / GNN architectures

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Lecheng Kong, Jiarui Feng, Hao Liu, Dacheng Tao, Yixin Chen, Muhan Zhang

NeurIPS 2023 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 5 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
replace random node marking (RNM) with RL-searched node tuples (ablation)MAG-GNN · SR25accuracy: 93.8 -> 100Improved
add RL search steps on one size-2 node tuple (ablation)MAG-GNN · SR25accuracyImproved
add RL search steps on one size-2 node tuple (ablation)MAG-GNN · EXP and CSLaccuracyImproved
pretrain on 6-CYCLES before training (ablation)MAG-GNN · ZINCMAE: 0.106 -> 0.096Improved
pretrain on 6-CYCLES before training (ablation)MAG-GNN · ZINC-FULLMAE: 0.030 -> 0.023Improved
pretrain on 6-CYCLES before training (ablation)MAG-GNN · OGBG-MOLHIVAUROC: 77.12 -> 78.30Improved
pretrain on 3-CYCLES before training (ablation)MAG-GNN · OGBG-MOLHIVAUROC: 77.12 -> 76.98No clear effect
pretrain on SR25 before training (ablation)MAG-GNN · ZINCMAE: 0.106 -> 0.103Improved
pretrain on SR25 before training (ablation)MAG-GNN · ZINC-FULLMAE: 0.030 -> 0.028Improved
use larger node tuples than size two for cycle countingMAG-GNN vs NGNN · 6-cyclesMAE: 0.0439 -> 0.0286Improved
use MAG-GNN instead of NGNNNGNN · QM9 U0MAE: 0.295 -> 0.111Improved
use MAG-GNN instead of full subgraph enumeration (I2GNN) for inferenceI2GNN · ZINC-FULLinference time (ms): 1864.1 -> 385.8Improved

Later papers that compared with this method

1 later accepted paper reports MAG-GNN as a baseline in their results tables; 1 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