---
title: "PAAL: Pattern-Anchor Alignment for Continual Knowledge Graph Embedding Under Structural Distribution Shift"
authors:
  - "Yue Jian"
  - "Lin Li"
  - "Kaize Shi"
  - "Junwei Zhou"
  - "Yu Yang"
doi: "10.24963/ijcai.2026/433"
url: "https://ijcai.org/proceedings/2026/433"
pdf: "https://ijcai.org/proceedings/2026/0433.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3890-3898"
track: "Main Track"
keywords:
  - "Knowledge Representation and Reasoning: Learning and reasoning"
---

# PAAL: Pattern-Anchor Alignment for Continual Knowledge Graph Embedding Under Structural Distribution Shift

Yue Jian, Lin Li, Kaize Shi, Junwei Zhou, Yu Yang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3890-3898. DOI: [10.24963/ijcai.2026/433](https://doi.org/10.24963/ijcai.2026/433)

## Abstract

Continual knowledge graph embedding (CKGE) has gained popularity for managing dynamic knowledge graphs. Unlike general graph continual-learning approaches, CKGE focuses on retaining triple-level knowledge, thereby overcoming the inability of static models to accommodate continuously arriving facts. However, as new fact triples come in, real-world knowledge graphs often experience structural distribution shifts: the underlying topology and the way facts interconnect evolve over time. This presents a challenge that the structural distribution of historical data may diverge from that of emerging data, creating a distributional mismatch that complicates the adaptation to new trends. To address this, we propose Pattern-Anchor Alignment (PAAL), which introduces relation-level structural anchors to explicitly model these structural shifts. By quantifying the alignment between the structural distribution of emerging triples and historical anchors, PAAL implements an alignment-modulated optimization strategy. It utilizes a calibrated gating mechanism to precisely regulate the intensity of historical constraints based on structural stability. Experimental results indicate the effectiveness of PAAL, showing average H@1 improvements of 11.77% and 9.29% on pattern-shift and standard CKGE benchmarks, respectively. Our code is available at https://github.com/cangjie553/PAAL.