Reimagining GNN Explanations with ideas from Tabular Data

Abstract

Explainability techniques for Graph Neural Networks still have a long way to go compared to explanations available for both neural and decision decision tree-based models trained on tabular data. Using a task that straddles both graphs and tabular data, namely Entity Matching, we comment on key aspects of explainability that are missing in GNN model explanations.

Anjali Singh

singhanj@usc.edu

My research interests include machine learning, natural language processing and software development.