Research map / Graph learning / GNN architectures
Towards Understanding and Reducing Graph Structural Noise for GNNs
Mingze Dong, Yuval Kluger
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 changed | Where | Measured | Effect |
|---|---|---|---|
| GPS graph rewiring (propensity-score based edge reweighting, ensembled with original graph) | GCN · WebKB (Cornell, Texas, Wisconsin) and Actor, Chameleon* | node classification accuracy: Cornell 43.5 to 74.6; Texas 66.2 to 80.0; Wisconsin 52.9 to 77.3 | Improved |
| GPS graph rewiring | GCN · Homophilic datasets (Cora, Citeseer, Pubmed) | node classification accuracy: Cora 81.7 to 80.5; Citeseer 71.8 to 71.5; Pubmed 78.9 to 77.7 | Hurt |
| k-NN graph rewiring on data features | GCN · Cornell | node classification accuracy: 43.5 to 68.6 | Improved |
| k-NN graph rewiring on data features | GCN · Cora | node classification accuracy: 81.7 to 48.0 | Hurt |
| GPS-rewired graph ESNR relationship to gains | GPS rewired graphs · Node classification benchmarks | correlation of ESNR with accuracy gain | Mixed |
| Edge dropout ratio increase (ESNR tracked) (ablation) | Cora, Citeseer, Pubmed with GCN · Planetoid edge dropout | ESNR and GCN accuracy | Improved |
| ESNR as metric (vs edge homophily) for GCN minus MLP accuracy difference (ablation) | 14 datasets · Cross-dataset GCN vs MLP | Pearson r: ESNR vs GCN r=0.85 vs EH vs GCN r=0.58 | Improved |
| Vanilla entry-wise SNR instead of ESNR (ablation) | Simulated CSBM · CSBM edge ratio sweep | consistency with GCN trend | Hurt |
Closest papers by meaning
- Training Robust Graph Neural Networks by Modeling Noise Dependencies (NeurIPS 2025 · similarity 0.88)
- NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise (NeurIPS 2024 · similarity 0.88)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.88)
- Locality-Aware Graph Rewiring in GNNs (ICLR 2024 · similarity 0.88)
- The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited (ICLR 2025 · similarity 0.88)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.87)
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.
