TransA: An Adaptive Approach for Knowledge Graph Embedding

Abstract

Knowledge representation is a major topic in AI, and many studies attempt to represent entities and relations of knowledge base in a continuous vector space. Among these attempts, translation-based methods build entity and relation vectors by minimizing the translation loss from a head entity to a tail one. In spite of the success of these methods, translation-based methods also suffer from the oversimplified loss metric, and are not competitive enough to model various and complex entities/relations in knowledge bases. To address this issue, we propose \textbf{TransA}, an adaptive metric approach for embedding, utilizing the metric learning ideas to provide a more flexible embedding method. Experiments are conducted on the benchmark datasets and our proposed method makes significant and consistent improvements over the state-of-the-art baselines.

References in corpus (1)

• Modeling Relation Paths for Representation Learning of Knowledge Bases

Cited by in corpus (15)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graph Self-Supervised Rationalization for Recommendation
• Representation Learning for Natural Language Processing
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• Knowledge Representation Learning: A Quantitative Review
• Matching Algorithms: Fundamentals, Applications and Challenges
• Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
• Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective
• Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN
• Joint Embedding Learning of Educational Knowledge Graphs
• Data Poisoning Attack against Knowledge Graph Embedding
• KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm
• Evaluating the Effectiveness of Margin Parameter when Learning Knowledge Embedding Representation for Domain-specific Multi-relational Categorized Data
• Inducing Interpretability in Knowledge Graph Embeddings
• A Probit Tensor Factorization Model For Relational Learning