SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy

TL;DR

SynergyKGC introduces an adaptive framework that effectively integrates entity semantics with diverse graph topologies, improving knowledge graph completion by reconciling heterogeneity and ensuring stable representations.

Contribution

It proposes a novel topology-aware synergy framework with relation-aware attention and density-dependent strategies to handle topological heterogeneity in KGC.

Findings

Significantly improves hit rates on benchmark datasets.

Effectively reconciles topological heterogeneity across graph densities.

Provides empirical evidence for resilient information integration.

Abstract

Knowledge Graph Completion (KGC) fundamentally hinges on the coherent fusion of pre-trained entity semantics with heterogeneous topological structures to facilitate robust relational reasoning. However, existing paradigms encounter a critical "structural resolution mismatch," failing to reconcile divergent representational demands across varying graph densities, which precipitates structural noise interference in dense clusters and catastrophic representation collapse in sparse regions. We present SynergyKGC, an adaptive framework that advances traditional neighbor aggregation to an active Cross-Modal Synergy Expert via relation-aware cross-attention and semantic-intent-driven gating. By coupling a density-dependent Identity Anchoring strategy with a Double-tower Coherent Consistency architecture, SynergyKGC effectively reconciles topological heterogeneity while ensuring representational stability across training and inference phases. Systematic evaluations on two public benchmarks validate the superiority of our method in significantly boosting KGC hit rates, providing empirical evidence for a generalized principle of resilient information integration in non-homogeneous structured data.