Research Overview: Higher Order Structures for Graph Explanations

This lecture from NPTEL-NOC IITM provides a comprehensive research overview of higher order structures for graph explanations, exploring the intersection of graph neural networks (GNNs) and explainability methods. Learn about advanced techniques for interpreting and explaining graph-based machine learning models through the lens of higher order structures. The 34-minute presentation delves into theoretical foundations and practical applications of graph explanations, offering valuable insights for researchers and practitioners working with graph data. Supplementary lecture materials are available for download to enhance understanding of these complex concepts.