AI Paper Atlas

Research map / Graph learning / GNN architectures

On the Power of Edge Independent Graph Models

Sudhanshu Chanpuriya, Cameron N Musco, Konstantinos Sotiropoulos, Charalampos Tsourakakis

NeurIPS 2021 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 1 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
Constrain an edge-independent model to bounded overlapEdge-independent graph models · Graphs generated by the modelexpected triangles: ≤ \frac{\sqrt{2}}{3} \cdot Ov(P)^{3/2} \cdot V(P)^{3/2}Hurt
Constrain an edge-independent model to bounded overlapEdge-independent graph models · Graphs generated by the modelexpected k-cycles: ≤ \frac{2^{k/2}}{2k} \cdot Ov(P)^{k/2} \cdot V(P)^{k/2}Hurt
Constrain an edge-independent model to bounded overlapEdge-independent graph models · Graphs generated by the model with V(P) \ge 2 nexpected global clustering coefficient: O \left (\frac{Ov(P)^{3/2} \cdot n}{V(P)^{1/2}} \right )Hurt
Use low overlapEdge-independent graph generative models · Cora-MLaverage triangles: 2,802 -> 1,461Hurt
Use low overlapEdge-independent graph generative models · Cora-MLaverage squares: 14,268 -> 6,880Hurt
Increase overlapEdge-independent graph generative models · Tested graph datasetstriangle countImproved
Use CCOP or HDOP, which match the input degree sequenceCCOP and HDOP · Tested graph datasets at overlap less than 0.2degree sequence matchImproved
Fix edges from high-degree nodesHDOP · Tested graph datasetstriangle densityImproved
Use TSVD instead of CELLTSVD · Tested graph datasetsdegree sequence matchImproved
Use TSVD instead of CELLTSVD · Tested graph datasetscharacteristic path lengthHurt
Use edge-independent random connectionsTested edge-independent graph models · Tested graph datasets except Web-Educharacteristic path lengthHurt

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