Measuring social bias in knowledge graph embeddings
It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks. However, to this point there has been no similar work done in the field of knowledge graph embeddings. We present the first study on social bias in knowledge graph embeddings, and propose a new metric suitable for measuring such bias. We conduct experiments on Wikidata and Freebase, and show that, as with word embeddings, harmful social biases related to professions are encoded in knowledge graph embeddings with respect to gender, religion, ethnicity and nationality. For example, knowledge graph embeddings encode the information that men are more likely to be bankers, and women more likely to be homekeepers. As knowledge graph embeddings become increasingly utilized, we suggest that it is important the existence of such biases are understood and steps taken to mitigate their impact.