{"type":"ScholarlyArticle","title":"PAAL: Pattern-Anchor Alignment for Continual Knowledge Graph Embedding Under Structural Distribution Shift","authors":[{"name":"Yue Jian","slug":"yue-jian","given":"Yue","family":"Jian","affiliation":""},{"name":"Lin Li","slug":"lin-li","given":"Lin","family":"Li","affiliation":""},{"name":"Kaize Shi","slug":"kaize-shi","given":"Kaize","family":"Shi","affiliation":""},{"name":"Junwei Zhou","slug":"junwei-zhou","given":"Junwei","family":"Zhou","affiliation":""},{"name":"Yu Yang","slug":"yu-yang","given":"Yu","family":"Yang","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/433","url":"https://ijcai.org/proceedings/2026/433","pdf":"https://ijcai.org/proceedings/2026/0433.pdf","markdown":"https://ijcai.org/proceedings/2026/433.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/433","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":433,"pages":{"first":3890,"last":3898},"keywords":["Knowledge Representation and Reasoning: Learning and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}