On Multi-Relational Link Prediction with Bilinear Models

Abstract

We study bilinear embedding models for the task of multi-relational link prediction and knowledge graph completion. Bilinear models belong to the most basic models for this task, they are comparably efficient to train and use, and they can provide good prediction performance. The main goal of this paper is to explore the expressiveness of and the connections between various bilinear models proposed in the literature. In particular, a substantial number of models can be represented as bilinear models with certain additional constraints enforced on the embeddings. We explore whether or not these constraints lead to universal models, which can in principle represent every set of relations, and whether or not there are subsumption relationships between various models. We report results of an independent experimental study that evaluates recent bilinear models in a common experimental setup. Finally, we provide evidence that relation-level ensembles of multiple bilinear models can achieve state-of-the art prediction performance.

Cited by in corpus (17)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Representation Learning for Dynamic Graphs: A Survey
• HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
• PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
• AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
• MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs
• Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective
• On Evaluating Embedding Models for Knowledge Base Completion
• Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
• Searching to Sparsify Tensor Decomposition for N-ary Relational Data
• A Relational Tucker Decomposition for Multi-Relational Link Prediction
• Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion
• Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
• Quadratic GCN for Graph Classification
• HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations
• Principled Representation Learning for Entity Alignment
• Rationalizing Medical Relation Prediction from Corpus-level Statistics