PiNet: A Permutation Invariant Graph Neural Network for Graph Classification
This work addresses the challenge of learning invariant representations for graph classification, which is important for applications like molecular analysis, but it is incremental as it builds on existing graph neural network methods.
The authors tackled the problem of graph classification with varying graph sizes by proposing PiNet, a permutation invariant graph neural network that uses a differentiable node attention pooling mechanism to learn fixed-size graph representations. They demonstrated statistically significant accuracy gains on isomorphic graph classification tasks with few training examples and achieved competitive performance on molecule datasets.
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.