Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework
This work addresses the challenge of making knowledge graphs more usable in intelligent systems like question answering, though it is incremental as it builds on existing adversarial learning approaches.
The paper tackles the problem of embedding knowledge graphs into continuous vector spaces to overcome their rigid symbolic nature, using a generative adversarial framework where a generative network creates vector representations for missing triple elements and a discriminative network scores triples, resulting in significant improvements over classical models like TransE on link prediction and triple classification tasks.
Many large-scale knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and decision support tasks. However, they are built on rigid symbolic frameworks which makes them hard to be used in other intelligent systems. We present a learning method using generative adversarial architecture designed to embed the entities and relations of the knowledge graphs into a continuous vector space. A generative network (GN) takes two elements of a (subject, predicate, object) triple as input and generates the vector representation of the missing element. A discriminative network (DN) scores a triple to distinguish a positive triple from those generated by GN. The training goal for GN is to deceive DN to make wrong classification. When arriving at a convergence, GN recovers the training data and can be used for knowledge graph completion, while DN is trained to be a good triple classifier. Unlike few previous studies based on generative adversarial architectures, our GN is able to generate unseen instances while they just use GN to better choose negative samples (already existed) for DN. Experiments demonstrate our method can improve classical relational learning models (e.g.TransE) with a significant margin on both the link prediction and triple classification tasks.