English

Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases

Machine Learning 2019-10-14 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1910.05030,
  title  = {Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases},
  author = {Maximilian Idahl and Megha Khosla and Avishek Anand},
  journal= {arXiv preprint arXiv:1910.05030},
  year   = {2019}
}

Comments

Accepted for poster presentation at ECML PKDD AIMLAI-XKDD workshop