Knowledge Graph Completion with Mixed Geometry Tensor Factorization
In this paper, we propose a new geometric approach for knowledge graph completion via low rank tensor approximation. We augment a pretrained and well-established Euclidean model based on a Tucker tensor decomposition with a novel hyperbolic interaction term. This correction enables more nuanced capturing of distributional properties in data better aligned with real-world knowledge graphs. By combining two geometries together, our approach improves expressivity of the resulting model achieving new state-of-the-art link prediction accuracy with a significantly lower number of parameters compared to the previous Euclidean and hyperbolic models.
Code (1)
Tasks
Knowledge Graph CompletionKnowledge GraphsLink PredictionTensor DecompositionWorld KnowledgeMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mixed-Curvature Multi-Relational Graph Neural Network for Knowledge Graph Completion
Knowledge graphs (KGs) have gradually become valuable assets for many AI applications. In a KG, a node denotes an entity, and an edge (or link) denotes a relationship between the entities represented by the nodes. Knowle…
Graph Neural NetworkKnowledge Graph CompletionKnowledge Graph EmbeddingsKnowledge GraphsFederated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization
Knowledge graphs (KGs), which consist of triples, are inherently incomplete and always require completion procedure to predict missing triples. In real-world scenarios, KGs are distributed across clients, complicating co…
Knowledge Graph CompletionKnowledge GraphsKnowledge Graph Completion as Tensor Decomposition: A Genreal Form and Tensor N-rank Regularization
Knowledge graph completion (KGC) is a 3rd-order binary tensor completion task. Tensor decomposition based (TDB) models have shown great performance in KGC. In this paper, we summarize existing TDB models and derive a gen…
FormKnowledge Graph CompletionTensor DecompositionDeterministic tensor completion with hypergraph expanders
We provide a novel analysis of low-rank tensor completion based on hypergraph expanders. As a proxy for rank, we minimize the max-quasinorm of the tensor, which generalizes the max-norm for matrices. Our analysis is dete…
LEMMAKnowledge Graph Completion based on Tensor Decomposition for Disease Gene Prediction
Accurate identification of disease genes has consistently been one of the keys to decoding a disease's molecular mechanism. Most current approaches focus on constructing biological networks and utilizing machine learning…
Knowledge Graph CompletionTensor Decomposition