Hybrid Directional Graph Neural Network for Molecules
Abstract
Equivariant message passing neural networks have emerged as the prevailing approach for predicting chemical properties of molecules due to their ability to leverage translation and rotation symmetries, resulting in a strong inductive bias. However, the equivariant operations in each layer can impose excessive constraints on the function form and network flexibility. To address these challenges, we introduce a novel network called the Hybrid Directional Graph Neural Network (HDGNN), which effectively combines strictly equivariant operations with learnable modules. We evaluate the performance of HDGNN on the QM9 dataset and the IS2RE dataset of OC20, demonstrating its state-of-the-art performance on several tasks and competitive performance on others. Our code is anonymously released on https://github.com/ajy112/HDGNN.
Cite
Text
An et al. "Hybrid Directional Graph Neural Network for Molecules." International Conference on Learning Representations, 2024.Markdown
[An et al. "Hybrid Directional Graph Neural Network for Molecules." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/an2024iclr-hybrid/)BibTeX
@inproceedings{an2024iclr-hybrid,
title = {{Hybrid Directional Graph Neural Network for Molecules}},
author = {An, Junyi and Qu, Chao and Zhou, Zhipeng and Cao, Fenglei and Yinghui, Xu and Qi, Yuan and Shen, Furao},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/an2024iclr-hybrid/}
}