Embedding Knowledge Graph in Function Spaces
This is an incremental improvement for knowledge graph representation learning, offering a novel functional approach that could benefit AI applications requiring complex relational reasoning.
The authors tackled knowledge graph embedding by proposing a method that operates in finite-dimensional function spaces instead of vector spaces, using polynomial functions and neural networks to enhance expressiveness and enable operations like composition and derivatives.
We introduce a novel embedding method diverging from conventional approaches by operating within function spaces of finite dimension rather than finite vector space, thus departing significantly from standard knowledge graph embedding techniques. Initially employing polynomial functions to compute embeddings, we progress to more intricate representations using neural networks with varying layer complexities. We argue that employing functions for embedding computation enhances expressiveness and allows for more degrees of freedom, enabling operations such as composition, derivatives and primitive of entities representation. Additionally, we meticulously outline the step-by-step construction of our approach and provide code for reproducibility, thereby facilitating further exploration and application in the field.