{"type":"ScholarlyArticle","title":"Higher-order Logical Knowledge Representation Learning","authors":[{"name":"Suixue Wang","slug":"suixue-wang","given":"Suixue","family":"Wang","affiliation":""},{"name":"Weiliang Huo","slug":"weiliang-huo","given":"Weiliang","family":"Huo","affiliation":""},{"name":"Shilin Zhang","slug":"shilin-zhang","given":"Shilin","family":"Zhang","affiliation":""},{"name":"Qingchen Zhang","slug":"qingchen-zhang","given":"Qingchen","family":"Zhang","affiliation":""}],"abstract":"Real-world knowledge graphs abound with higher-order logical relations that simple triples, limited to pairwise connections, fail to represent. Thus, capturing higher-order logical relations involving multiple entities has garnered significant attention. However, existing methods ignore the structural information in higher-order relations. To this end, we propose a higher-order logical knowledge representation learning method, named LORE, which leverages network motifs, the patterns/subgraphs that naturally capture the structural information in graphs, to extract higher-order features and ultimately, learn effective representations of knowledge graphs. Compared to existing approaches, LORE aggregates the attribute features of entities with the extracted higher-order logical relations to form enhanced representations of knowledge graphs. In particular, three aggregators (i.e., Hadamard, Connection, and Summation) are proposed and employed. Extensive experiments have been conducted on six real-world datasets for two downstream tasks (i.e., entity classification and link prediction). The results show that LORE outperforms baselines significantly and consistently.","doi":"10.24963/ijcai.2025/378","url":"https://ijcai.org/proceedings/2025/378","pdf":"https://ijcai.org/proceedings/2025/0378.pdf","markdown":"https://ijcai.org/proceedings/2025/378.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/378","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":378,"pages":{"first":3398,"last":3406},"keywords":["Data Mining: DM: Knowledge graphs and knowledge base completion","Computer Vision: CV: Representation learning","Machine Learning: ML: Representation learning","Knowledge Representation and Reasoning: KRR: Knowledge representation languages"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}