Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases
This addresses the interpretability challenge in graph machine learning for researchers and practitioners, but it is incremental as it builds on existing embedding methods.
The paper tackles the problem of explaining node embeddings by identifying human-interpretable subspaces within unsupervised node representations, using an external knowledge base as a guide, and reports low error in finding fine-grained concepts.
In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide to identify subspaces in node embeddings learned from an entity graph derived from Wikipedia. We propose a method that given a concept finds a linear transformation to a subspace where the structure of the concept is retained. Our initial experiments show that we obtain low error in finding fine-grained concepts.