# Image-Like Graph Representations for Improved Molecular Property Prediction

arXiv: https://arxiv.org/abs/2111.10695 · HTML: https://mlsanity.com/paper/2111.10695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 20 Nov 2021.

## Builds on (most cited first, 9 of 9)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [On the Bottleneck of Graph Neural Networks and its Practical Implications](https://mlsanity.com/paper/2006.05205/) (2020)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Order Matters: Sequence to sequence for sets](https://mlsanity.com/paper/1511.06391/) (2015)
- [LanczosNet: Multi-Scale Deep Graph Convolutional Networks](https://mlsanity.com/paper/1901.01484/) (2019)
- [Path-Augmented Graph Transformer Network](https://mlsanity.com/paper/1905.12712/) (2019)
- [Neural Message Passing on High Order Paths](https://mlsanity.com/paper/2002.10413/) (2020)
- [Gated Graph Recursive Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/1909.00259/) (2019)

## Abstract (arXiv)

Research into deep learning models for molecular property prediction has primarily focused on the development of better Graph Neural Network (GNN) architectures. Though new GNN variants continue to improve performance, their modifications share a common theme of alleviating problems intrinsic to their fundamental graph-to-graph nature. In this work, we examine these limitations and propose a new molecular representation that bypasses the need for GNNs entirely, dubbed CubeMol. Our fixed-dimensional stochastic representation, when paired with a transformer model, exceeds the performance of state-of-the-art GNN models and provides a path for scalability.