# PiNet: A Permutation Invariant Graph Neural Network for Graph Classification

arXiv: https://arxiv.org/abs/1905.03046 · HTML: https://mlsanity.com/paper/1905.03046/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2019.

## Built on by (most cited first, 3 of 3)

- [Reversible Action Design for Combinatorial Optimization with Reinforcement Learning](https://mlsanity.com/paper/2102.07210/) (2021)
- [CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs](https://mlsanity.com/paper/2311.09690/) (2023)
- [Simplicity within biological complexity](https://mlsanity.com/paper/2405.09595/) (2024)

## Abstract (arXiv)

We propose an end-to-end deep learning learning model for graph classification and representation learning that is invariant to permutation of the nodes of the input graphs. We address the challenge of learning a fixed size graph representation for graphs of varying dimensions through a differentiable node attention pooling mechanism. In addition to a theoretical proof of its invariance to permutation, we provide empirical evidence demonstrating the statistically significant gain in accuracy when faced with an isomorphic graph classification task given only a small number of training examples. We analyse the effect of four different matrices to facilitate the local message passing mechanism by which graph convolutions are performed vs. a matrix parametrised by a learned parameter pair able to transition smoothly between the former. Finally, we show that our model achieves competitive classification performance with existing techniques on a set of molecule datasets.