# Training Sensitivity in Graph Isomorphism Network

arXiv: https://arxiv.org/abs/2008.09020 · HTML: https://mlsanity.com/paper/2008.09020/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 2 of 2)

- [When Do Flat Minima Optimizers Work?](https://mlsanity.com/paper/2202.00661/) (2022)
- [A Comprehensive Analytical Survey on Unsupervised and Semi-Supervised Graph Representation Learning Methods](https://mlsanity.com/paper/2112.10372/) (2021)

## Abstract (arXiv)

Graph neural network (GNN) is a popular tool to learn the lower-dimensional representation of a graph. It facilitates the applicability of machine learning tasks on graphs by incorporating domain-specific features. There are various options for underlying procedures (such as optimization functions, activation functions, etc.) that can be considered in the implementation of GNN. However, most of the existing tools are confined to one approach without any analysis. Thus, this emerging field lacks a robust implementation ignoring the highly irregular structure of the real-world graphs. In this paper, we attempt to fill this gap by studying various alternative functions for a respective module using a diverse set of benchmark datasets. Our empirical results suggest that the generally used underlying techniques do not always perform well to capture the overall structure from a set of graphs.