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 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 the embeddings with respect to gender, religion, ethnicity and nationality. For example, graph embeddings encode the information that men are more likely to be bankers, and women more likely to be homekeepers. As 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge Graph EmbeddingsWord EmbeddingsSimilar Papers 제목 키워드 기반
Measuring Social Biases in Grounded Vision and Language Embeddings
We generalize the notion of social biases from language embeddings to grounded vision and language embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungroun…
Word EmbeddingsAdversarial Learning for Debiasing Knowledge Graph Embeddings
Knowledge Graphs (KG) are gaining increasing attention in both academia and industry. Despite their diverse benefits, recent research have identified social and cultural biases embedded in the representations learned fro…
AttributeKnowledge Graph EmbeddingsKnowledge GraphsLink PredictionA Comparative Study on Word Embeddings and Social NLP Tasks
In recent years, gray social media platforms, those with a loose moderation policy on cyberbullying, have been attracting more users. Recently, data collected from these types of platforms have been used to pre-train wor…
Word EmbeddingsDebiasing knowledge graph embeddings
It has been shown that knowledge graph embeddings encode potentially harmful social biases, such as the information that women are more likely to be nurses, and men more likely to be bankers. As graph embeddings begin to…
Knowledge Graph EmbeddingsBiased Embeddings from Wild Data: Measuring, Understanding and Removing
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data that has been gathered "from the wild" …