SOURCE-LINKED INTELLIGENCE

Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forgetting, but entity admission also changes the candidate universe of every compatible query. A historical answer can therefore lose rank even when its score and its ordering among old entities are preserved. We formalize this effect as candidate-set interference and introduce Matched Excess-Outranker Regularization (MEOR), a host-level objective that compares smooth answer-relative newcomer pressure with score-blind, structurally matched old refer

Read original source ↗ Open in workspace

recordType

paper

region

Global