AI Paper Atlas

Research map / Graph learning / GNN architectures

Self-supervised Graph Neural Networks via Low-Rank Decomposition

Liang Yang, Runjie Shi, Qiuliang Zhang, Bingxin Niu, Zhen Wang, Xiaochun Cao, Chuan Wang

NeurIPS 2023 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 0 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
use tensor decomposition with similar ego-networks instead of matrix decomposition (ablation)LRD-GNN · Wiki-CSaccuracy (%): 80.19±0.18 -> 81.43±0.13Improved
use tensor decomposition instead of matrix decomposition (ablation)LRD-GNN · Squirrelaccuracy (%): 47.64±1.21 -> 55.91±0.91Improved
use tensor decomposition instead of matrix decomposition (ablation)LRD-GNN · Chameleonaccuracy (%): 60.71±2.21 -> 66.27±1.27Improved
use tensor decomposition instead of matrix decomposition (ablation)LRD-GNN · Actoraccuracy (%): 37.22±0.83 -> 37.07±0.83No clear effect
use tensor decomposition instead of matrix decomposition (ablation)LRD-GNN · Cornellaccuracy (%): 78.48±0.36 -> 84.73±2.83Improved
LRD-GNN-Tensor vs best SSL baseline GRACE-FALRD-GNN-Tensor · Chameleonaccuracy (%): 52.68±2.14 -> 66.27±1.27Improved
LRD-GNN-Tensor vs BGRLLRD-GNN-Tensor · Coraaccuracy (%): 81.08±0.17 -> 83.74±0.61Improved
LRD-GNN-Tensor vs BGRLLRD-GNN-Tensor · Amazon Photoaccuracy (%): 93.24±0.29 -> 93.26±0.15No clear effect
LRD-GNN-Tensor vs BGRLLRD-GNN-Tensor · PubMedaccuracy (%): 79.97±0.36 -> 79.71±0.75Hurt
build tensor from attribute-similar nodes instead of structure-similar nodes (ablation)LRD-GNN · Coraaccuracy (%): 78.20±0.65 -> 83.74±0.61Improved
drop A2X (higher-order information) from tensor variants (ablation)LRD-GNN · Coraaccuracy (%): 83.74±0.61 -> 83.55±0.27No clear effect
remove raw attributes X and use only propagated features AX, A2X (ablation)LRD-GNN · Coraaccuracy (%): 83.74±0.61 -> 80.32±0.49Hurt

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