# Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression

arXiv: https://arxiv.org/abs/2209.13410 · HTML: https://mlsanity.com/paper/2209.13410/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 24 Sep 2022.

## Builds on (most cited first, 29 of 29)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training](https://mlsanity.com/paper/2009.03294/) (2020)
- [Meta-Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1808.08437/) (2018)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [Graph Meta Learning via Local Subgraphs](https://mlsanity.com/paper/2006.07889/) (2020)
- [Few-Shot Graph Learning for Molecular Property Prediction](https://mlsanity.com/paper/2102.07916/) (2021)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [Message passing all the way up](https://mlsanity.com/paper/2202.11097/) (2022)
- [Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems](https://mlsanity.com/paper/2103.04490/) (2021)
- [Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models](https://mlsanity.com/paper/1906.09427/) (2019)
- [MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records](https://mlsanity.com/paper/1905.03218/) (2019)
- [Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures](https://mlsanity.com/paper/2002.12815/) (2020)
- [Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems](https://mlsanity.com/paper/1905.05644/) (2019)
- [Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors](https://mlsanity.com/paper/2003.04663/) (2020)
- [Meta-Inductive Node Classification across Graphs](https://mlsanity.com/paper/2105.06725/) (2021)
- [A Meta-Learning Approach for Training Explainable Graph Neural Networks](https://mlsanity.com/paper/2109.09426/) (2021)
- [Meta-QSAR: a large-scale application of meta-learning to drug design and discovery](https://mlsanity.com/paper/1709.03854/) (2017)
- [A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings](https://mlsanity.com/paper/2012.06755/) (2020)
- [Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction](https://mlsanity.com/paper/2003.05996/) (2020)
- [Meta-Learning with Graph Neural Networks: Methods and Applications](https://mlsanity.com/paper/2103.00137/) (2021)
- [Structure-Enhanced Meta-Learning For Few-Shot Graph Classification](https://mlsanity.com/paper/2103.03547/) (2021)

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

- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey](https://mlsanity.com/paper/2402.07249/) (2024)

## Abstract (arXiv)

We demonstrate the applicability of model-agnostic algorithms for meta-learning, specifically Reptile, to GNN models in molecular regression tasks. Using meta-learning we are able to learn new chemical prediction tasks with only a few model updates, as compared to using randomly initialized GNNs which require learning each regression task from scratch. We experimentally show that GNN layer expressivity is correlated to improved meta-learning. Additionally, we also experiment with GNN emsembles which yield best performance and rapid convergence for k-shot learning.