AI Paper Atlas

Research map / Graph learning / GNN architectures

coVariance Neural Networks

Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro

NeurIPS 2022 · Graph learning › GNN architectures · approach: Oversmoothing and heterophily · 2 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
VNN instead of PCA-LRage regression · FTDC100MAE: 5.19 -> 4.31Improved
VNN instead of PCA-LRage regression · FTDC300MAE: 5.97 -> 4.45Improved
VNN instead of PCA-LRage regression · FTDC500MAE: 5.31 -> 4.74Improved
VNN instead of PCA-rbfage regression · FTDC100MAE: 4.49 -> 4.31Improved
VNN instead of PCA-rbfage regression · FTDC300MAE: 4.64 -> 4.45Improved
VNN instead of PCA-rbfage regression · FTDC500MAE: 4.38 -> 4.74Hurt
VNN instead of PCA-rbfage regression · FTDC300correlation: 0.61 -> 0.62No clear effect
perturb sample covariance matrix (add/remove samples)PCA-regression · ABC test setMAEHurt
perturb sample covariance matrixVNN · ABC test setMAENo clear effect
reduce sample size below 50 for covariance (ablation)VNN · ABC test setMAEHurt
perturb covariance matrix with rbf regressionPCA-rbf · FTDC100/300MAENo clear effect
transfer VNN across FTDC resolutions without retrainingVNN · FTDC100/300/500MAE and correlationNo clear effect

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