TransA: An Adaptive Approach for Knowledge Graph Embedding
This addresses the problem of modeling complex entities and relations in knowledge bases for AI researchers, representing an incremental advancement in embedding techniques.
The paper tackles the oversimplified loss metric in translation-based knowledge graph embedding methods by proposing TransA, an adaptive metric approach that achieves significant and consistent improvements over state-of-the-art baselines on benchmark datasets.
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.