AI Paper Atlas

Research map / Graph learning / GNN architectures

Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features

Jiuhai Chen, Jonas Mueller, Vassilis N. Ioannidis, Soji Adeshina, Yangkun Wang, Tom Goldstein, David Wipf

ICLR 2022 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 0 citations (OpenAlex)

Read the paper

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
interleave graph propagation with boosting instead of applying propagation only after CatBoost training (ablation)CatBoost/EBBS · House, County, VK, AvazuRMSE: 0.54 -> 0.45; 1.25 -> 1.11; 6.96 -> 6.90; 0.1083 -> 0.1062Improved
interleave graph propagation with boosting instead of applying propagation only after CatBoost training (ablation)CatBoost/EBBS · SLAP, DBLPaccuracy: 96.2 -> 96.3; 90.7 -> 91.3Mixed
interleave graph propagation with boosting instead of applying propagation only after CatBoost training (ablation)CatBoost/EBBS · Coauthor-CS, Coauthor-Phyaccuracy: 94.6 -> 94.9; 96.4 -> 96.9Improved
reduce BGNN to one SGD step per iteration (ablation)BGNN · House, County, VK, AvazuRMSE: 0.50 -> 0.56; 1.26 -> 1.34; 6.95 -> 7.28; 0.1090 -> 0.110Hurt
remove end-to-end training (ablation)BGNN · House, County, VK, AvazuRMSE: 0.50 -> 0.51; 1.26 -> 1.33; 6.95 -> 7.07; 0.1090 -> 0.1095Mixed
use graph propagation with boosted tabular featuresEBBS · OGB-ArXivaccuracy: 67.0 -> 70.10Improved
use EBBS instead of the strongest reported non-EBBS methodEBBS · House, County, VK, AvazuRMSE: 0.50 -> 0.45; 1.25 -> 1.11; 6.95 -> 6.90; 0.1083 -> 0.1062Improved
use EBBS instead of the strongest reported non-EBBS methodEBBS · SLAP, DBLP, Coauthor-CS, Coauthor-Phyaccuracy: 96.3 -> 96.3; 91.3 -> 91.3; 94.6 -> 94.9; 96.9 -> 96.9Mixed

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