Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization

arXiv:2610.36204v1 Announce Type: cross Abstract: Link prediction remains difficult in sparse graphs, where diffusion heuristics lack connectivity and geometric methods suffer spectral instability when coupling learned representations with diffusion operators. We introduce Concorde, an energy-based framework that resolves this by decomposing link likelihood into three structurally decoupled branches: (i) a parameter-free spectral anchor that establishes permutation-invariant topological stability; (ii) a mixed-curvature residual on a learnable H^{d_h}{c_h} imes S^{d_s}{c_s} product manifold, regularized by a feature-aware Ollivier-Ricci curvature proxy; and (iii) a continuous vector field on the tangent bundle of hyperbolic space for non-local structural alignment across topological gaps. The branches are fused via learned gating and trained with an N-pair ranking loss aligned with retrieval-style evaluation. Across five benchmarks spanning sparse, dense, featureless, and attributed regimes, Concorde establishes state-of-the-art early retrieval precision, nearly doubling P@10% over leading baselines in sparse settings.

Related

• TRACE: Topology-Aware Reconnection via Prediction-Adaptive Connectivity Enforcement for Thin-Structure Segmentation
• Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability
• Dual-Level Atomic and Coordination Geometry Learning for Crystal Property Prediction Using Graph Neural Networks

Source: arXiv cs.AI | 2026-10-28