Reimagining GNN Explanations with ideas from Tabular Data

Autor:	Singh, Anjali, K, Shamanth R Nayak, Ganesan, Balaji
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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. Comment: 4 pages, 8 figures, XAI Workshop at ICML 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.12665 Zobrazit plný text záznamu View this record from Arxiv