AI Paper Atlas

Research map / Graph learning / GNN architectures

EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks

Runlin Lei, Zhen WANG, Yaliang Li, Bolin Ding, Zhewei Wei

NeurIPS 2022 · Graph learning › GNN architectures · approach: Oversmoothing and heterophily · 15 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
discard odd-order terms from polynomial filter (GPRGNN -> EvenNet)GPRGNN · cSBM phi_train=0.75, phi_test=-0.75accuracy (%): 53.52 -> 94.59Improved
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · cSBM phi_train=phi_test=0.75accuracy (%): 95.93 -> 95.29No clear effect
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · Meta-cora poison attackaccuracy (%): 76.27 -> 77.74Improved
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · MM-citeseer poison attackaccuracy (%): 72.81 -> 73.51Improved
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · clean Coraaccuracy (%): 88.34 -> 87.25Hurt
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · clean Squirrelaccuracy (%): 51.93 -> 49.80Hurt
discard odd-order terms (GPRGNN -> EvenNet)GPRGNN · clean Texasaccuracy (%): 93.44 -> 93.77Improved
hard-remove odd orders (EvenNet) vs soft L1 penalty on odd coefficients (EvenReg) (ablation)EvenNet · cSBM phi_train=0.50, phi_test=-0.50accuracy (%): 78.06 -> 82.57Improved
add L1 penalty on odd coefficients to full-order filter (GPRGNN -> EvenReg) (ablation)GPRGNN · cSBM phi_train=0.50, phi_test=-0.50accuracy (%): 56.16 -> 78.06Improved
use even-hop (2-hop) vs 1-hop homophily (ablation)graph attacks · Meta/MinMax poisoned Cora, Citeseer, ACMhomophily gap: 0.28 -> 0.13 (Meta-Cora)Improved

Later papers that compared with this method

4 later accepted papers report EvenNet as a baseline in their results tables; 3 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