Explainable Link Prediction

Описание: Learning graph representations from n-ary relational data and predicting links between entities has a number of real world applications in anti-money laundering, fraud detection, sales recommendations, etc. In this demo, we present our latest research to predict links between entities in TACRED dataset (as an example use case) using graph neural networks along with human understandable explanations for the predicted links. We also present GraphSheets, a checklist for model developers to ensure that link prediction remains fair, privacy preserving, and ethical.