# Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization

arXiv: https://arxiv.org/abs/1906.05488 · HTML: https://mlsanity.com/paper/1906.05488/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 10 of 10)

- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [3D Infomax improves GNNs for Molecular Property Prediction](https://mlsanity.com/paper/2110.04126/) (2021)
- [Systematic Generalization with Edge Transformers](https://mlsanity.com/paper/2112.00578/) (2021)
- [Deep Learning Methods for Small Molecule Drug Discovery: A Survey](https://mlsanity.com/paper/2303.00313/) (2023)
- [GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework](https://mlsanity.com/paper/2112.10767/) (2021)
- [Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure](https://mlsanity.com/paper/2201.00668/) (2022)
- [Multiparameter Persistent Homology for Molecular Property Prediction](https://mlsanity.com/paper/2311.10808/) (2023)
- [SE(3)-Invariant Multiparameter Persistent Homology for Chiral-Sensitive Molecular Property Prediction](https://mlsanity.com/paper/2312.07633/) (2023)
- [Measuring and Improving the Use of Graph Information in Graph Neural Networks](https://mlsanity.com/paper/2206.13170/) (2022)
- [Deep Learning-Derived Optimal Aviation Strategies to Control Pandemics](https://mlsanity.com/paper/2210.10888/) (2022)

## Abstract (arXiv)

Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far from being optimal since they do not fully utilize the relational information between nodes. We propose the information maximizing graph neural networks (IGNN), which maximizes the mutual information between edge states and transform parameters. We reformulate the mutual information as a differentiable objective via a variational approach. We compare our model against several recent variants of GNNs and show that our model achieves the state-of-the-art performance on multiple tasks including quantum chemistry regression on QM9 dataset, generalization capability from QM9 to larger molecular graphs, and prediction of molecular bioactivities relevant for drug discovery. The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work. To encourage more future work in this area, all datasets and codes used in this paper will be released for public access.