AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Metropolis-Hastings Data Augmentation for Graph Neural Networks

Hyeonjin Park, Seunghun Lee, Sihyeon Kim, Jinyoung Park, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim

NeurIPS 2021 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 7 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 MH-Aug augmentation with consistency and entropy regularizers (w/ Reg)vanilla GCN/GraphSAGE/GAT · five node classification datasetsaccuracy: 3.16% on averageImproved
MH-Aug (w/ Reg) instead of vanillaGraphSAGE · CORAaccuracy: 79.78 -> 84.70Improved
MH-Aug (w/ Reg) instead of vanillaGCN, GraphSAGE, GAT · CITESEERaccuracy: 4.16%Improved
remove regularizers (supervised only, MH-Aug w/o Reg) vs vanilla (ablation)MH-Aug · five datasetsaccuracy: 1.47% on averageImproved
MH-Aug (w/o Reg) instead of vanilla GAT (ablation)GAT · Computersaccuracy: 78.47 -> 81.72Improved
MH-Aug (w/o Reg) instead of DropEdgeGCN · CORAaccuracy: 82.21 -> 83.55Improved
add consistency and entropy regularizers to MH-Aug (ablation)MH-Aug with GCN · CORAaccuracy: 83.55 -> 85.16Improved
add regularizers to MH-Aug (ablation)MH-Aug with GraphSAGE · Photoaccuracy: 90.37 -> 92.19Improved
AdaEdge instead of vanillaGAT · CORAaccuracy: 82.23 -> 77.90Hurt
remove normalization term by number of possible augmented graphs from target distribution (ablation)MH-Aug target distribution · fully connected 100-node graphmean ego-graph change ratioHurt
increase sigma_E to 1000 (ego-graph diversity) (ablation)MH-Aug · CORA ego-graph samplesedge-drop probabilityMixed

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