QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion
Knowledge graph embedding has been an active research topic for knowledge base completion (KGC), with progressive improvement from the initial TransE, TransH, RotatE et al to the current state-of-the-art QuatE. However, QuatE ignores the multi-faceted nature of the entity and the complexity of the relation, only using rigorous operation on quaternion space to capture the interaction between entitiy pair and relation, leaving opportunities for better knowledge representation which will finally help KGC. In this paper, we propose a novel model, QuatDE, with a dynamic mapping strategy to explicitly capture the variety of relational patterns and separate different semantic information of the entity, using transition vectors to adjust the point position of the entity embedding vectors in the quaternion space via Hamilton product, enhancing the feature interaction capability between elements of the triplet. Experiment results show QuatDE achieves state-of-the-art performance on three well-established knowledge graph completion benchmarks. In particular, the MR evaluation has relatively increased by 26% on WN18 and 15% on WN18RR, which proves the generalization of QuatDE.
Code (1)
Tasks
Graph EmbeddingKnowledge Base CompletionKnowledge Graph CompletionKnowledge Graph EmbeddingLink PredictionRelationTripletMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
QuatRE: Relation-Aware Quaternions for Knowledge Graph Embeddings
We propose a simple yet effective embedding model to learn quaternion embeddings for entities and relations in knowledge graphs. Our model aims to enhance correlations between head and tail entities given a relation with…
Knowledge Graph CompletionKnowledge Graph EmbeddingsKnowledge GraphsRelationQuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding
Knowledge graph embedding (KGE) methods aim to represent entities and relations in a continuous space while preserving their structural and semantic properties. Quaternion-based KGEs have demonstrated strong potential in…
Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingDistance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation
Quaternion contains one real part and three imaginary parts, which provided a more expressive hypercomplex space for learning knowledge graph. Existing quaternion embedding models measure the plausibility of a triplet ei…
Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingLink Prediction+2Quaternion Knowledge Graph Embeddings
In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings. More specifically, qua…
Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingKnowledge Graph Embeddings+3Quaternion Graph Neural Networks
Recently, graph neural networks (GNNs) have become an important and active research direction in deep learning. It is worth noting that most of the existing GNN-based methods learn graph representations within the Euclid…
General ClassificationGraph ClassificationGraph EmbeddingKnowledge Graph Completion+4