AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction

Jinkyu Sung, Myunggeum Jee, Joonseok Lee

ICLR 2026 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 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
replace SNEA's two-stage pipeline with Gaussian copula edge correlation modelSNEA backbone · WikiRfatotal training time (sec): 2174.1 -> 18.0Improved
replace SNEA with CopulaLSPSNEA backbone · Epinionstotal training time (sec): 6574.4 -> 24.7Improved
replace SNEA with CopulaLSPSNEA backbone · BitcoinAlphaMacro F1: 0.669 -> 0.716Improved
replace SNEA with CopulaLSPSNEA backbone · BitcoinAlphaAUC: 0.866 -> 0.864No clear effect
replace SNEA with CopulaLSPSNEA backbone · EpinionsGPU memory (GB), training: 7.03 -> 7.20Hurt
learn Gramian correlation instead of identity (no correlation) (ablation)CopulaLSP · BitcoinAlphaMacro F1: 0.665 -> 0.713Improved
learn Gramian correlation instead of identity (no correlation) (ablation)CopulaLSP · EpinionsMacro F1: 0.782 -> 0.810Improved
learn Gramian correlation instead of identity (no correlation) (ablation)CopulaLSP · BitcoinAlpha, BitcoinOTC, WikiElec, WikiRfa, SlashDot, EpinionsAUC: 0.830 -> 0.865 (BitcoinAlpha); others within 0.001No clear effect
learn Gramian correlation instead of identity (no correlation) (ablation)CopulaLSP · WikiElecepochs to converge: 136.5 -> 204.6Hurt
learn Gramian correlation instead of identity (no correlation) (ablation)CopulaLSP · Epinionsepochs to converge: 127.2 -> 58.2Improved
add Woodbury reformulation for inference (ablation)CopulaLSP · BitcoinOTCinference time (sec): 0.64 -> 0.07Improved
add Woodbury reformulation for inference (ablation)CopulaLSP · Epinionsinference GPU memory (GB): 1182.54 -> 6.18Improved

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