Position-Aware Relational Transformer for Knowledge Graph Embedding

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 8; pp. 11580 - 11594
• Main Authors: Li, Guangyao, Sun, Zequn, Hu, Wei, Cheng, Gong, Qu, Yuzhong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2024
• Subjects: Encoding; Entity alignment; knowledge graph (KG) embedding; Knowledge graphs; link prediction; position encoding; Predictive models; Semantics; Task analysis; Training; Transformer; Transformers

Although Transformer has achieved success in language and vision tasks, its capacity for knowledge graph (KG) embedding has not been fully exploited. Using the self-attention (SA) mechanism in Transformer to model the subject-relation-object triples in KGs suffers from training inconsistency as SA i...