# The Importance of Model Inspection for Better Understanding Performance Characteristics of Graph Neural Networks

arXiv: https://arxiv.org/abs/2405.01270 · HTML: https://mlsanity.com/paper/2405.01270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Risk of Bias in Chest Radiography Deep Learning Foundation Models](https://mlsanity.com/paper/2209.02965/) (2022)
- [Data Augmentation for Graph Classification](https://mlsanity.com/paper/2009.09863/) (2020)
- [A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimaging](https://mlsanity.com/paper/2210.16670/) (2022)

## Abstract (arXiv)

This study highlights the importance of conducting comprehensive model inspection as part of comparative performance analyses. Here, we investigate the effect of modelling choices on the feature learning characteristics of graph neural networks applied to a brain shape classification task. Specifically, we analyse the effect of using parameter-efficient, shared graph convolutional submodels compared to structure-specific, non-shared submodels. Further, we assess the effect of mesh registration as part of the data harmonisation pipeline. We find substantial differences in the feature embeddings at different layers of the models. Our results highlight that test accuracy alone is insufficient to identify important model characteristics such as encoded biases related to data source or potentially non-discriminative features learned in submodels. Our model inspection framework offers a valuable tool for practitioners to better understand performance characteristics of deep learning models in medical imaging.