AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization

Ege Demirci, Ambuj K Singh

NeurIPS 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Concorde, an energy-based link prediction framework that decomposes link likelihood into three decoupled branches, including a parameter-free spectral anchor, to address spectral instability in sparse graphs.

Problem

Link prediction in sparse graphs, where diffusion heuristics lack connectivity and geometric methods suffer spectral instability when coupling learned representations with diffusion operators.

Approach

Decomposes link likelihood into three structurally decoupled branches within an energy-based framework, with a parameter-free spectral anchor as one branch, avoiding instability from coupling learned representations with diffusion operators.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add mixed-curvature residual branch (ablation)Concorde · CiteSeerAP: 2.59 -> 5.05Improved
add mixed-curvature residual branch (ablation)Concorde · PowerAP: 2.72 -> 6.39Improved
add non-local geodesic steering field (ablation)Concorde · PowerAP: 4.17 -> 6.39Improved
add non-local geodesic steering field (ablation)Concorde · OGBL-DDIAP: 38.38 -> 42.32Improved
add residual and field branches on top of invariant anchor (ablation)Concorde · OGBL-DDIAP: 28.70 -> 42.32Improved
use product manifold H x S instead of Euclidean latent (ablation)Concorde residual · OGBL-DDIAP: 38.52 -> 42.32Improved
use product manifold H x S instead of Euclidean latent (ablation)Concorde residual · PowerAP: 5.85 -> 6.39Improved
include hyperbolic component (vs spherical only) (ablation)Concorde residual · PowerAP: 5.78 -> 6.39Improved
include spherical component (vs hyperbolic only) (ablation)Concorde residual · OGBL-DDIAP: 38.32 -> 42.32Improved
add feature-aware Ollivier-Ricci curvature proxy (ablation)Concorde residual · OGBL-DDIAP: 39.22 -> 42.32Improved
add local neighborhood geometry statistics (ablation)Concorde residual · PowerAP: 4.85 -> 6.39Improved
add geometry on top of same-loss learned reweighting (ablation)Concorde · OGBL-DDIAP: 38.15 -> 42.32Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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