Link Prediction using Embedded Knowledge Graphs
This addresses the issue of incomplete knowledge bases for AI systems, offering a more efficient alternative to path-based methods.
The paper tackles the problem of knowledge base completion by proposing an embedded knowledge graph network (EKGN) that performs interactive lookups on a compressed, trained graph, achieving new state-of-the-art results on benchmarks.
Since large knowledge bases are typically incomplete, missing facts need to be inferred from observed facts in a task called knowledge base completion. The most successful approaches to this task have typically explored explicit paths through sequences of triples. These approaches have usually resorted to human-designed sampling procedures, since large knowledge graphs produce prohibitively large numbers of possible paths, most of which are uninformative. As an alternative approach, we propose performing a single, short sequence of interactive lookup operations on an embedded knowledge graph which has been trained through end-to-end backpropagation to be an optimized and compressed version of the initial knowledge base. Our proposed model, called Embedded Knowledge Graph Network (EKGN), achieves new state-of-the-art results on popular knowledge base completion benchmarks.