# ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery

arXiv: https://arxiv.org/abs/2506.11041 · HTML: https://mlsanity.com/paper/2506.11041/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network](https://mlsanity.com/paper/1709.04555/) (2017)
- [Mapping the Space of Chemical Reactions Using Attention-Based Neural Networks](https://mlsanity.com/paper/2012.06051/) (2020)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [Overlapping Community Detection with Graph Neural Networks](https://mlsanity.com/paper/1909.12201/) (2019)
- [Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search](https://mlsanity.com/paper/2407.06334/) (2024)
- [AHP: Learning to Negative Sample for Hyperedge Prediction](https://mlsanity.com/paper/2204.06353/) (2022)
- [ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation](https://mlsanity.com/paper/2409.12010/) (2024)
- [A Survey on Hyperlink Prediction](https://mlsanity.com/paper/2207.02911/) (2022)
- [Molecular Hypergraph Neural Networks](https://mlsanity.com/paper/2312.13136/) (2023)
- [Are we making much progress? Revisiting chemical reaction yield prediction from an imbalanced regression perspective](https://mlsanity.com/paper/2402.05971/) (2024)
- [AI-driven Hypergraph Network of Organic Chemistry: Network Statistics and Applications in Reaction Classification](https://mlsanity.com/paper/2208.01647/) (2022)
- [Hypergraph: A Unified and Uniform Definition with Application to Chemical Hypergraph and More](https://mlsanity.com/paper/2405.12235/) (2024)

## Built on by (most cited first, 1 of 1)

- [CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?](https://mlsanity.com/paper/2511.09483/) (2025)

## Abstract (arXiv)

Reaction virtual screening and discovery are fundamental challenges in chemistry and materials science, where traditional graph neural networks (GNNs) struggle to model multi-reactant interactions. In this work, we propose ChemHGNN, a hypergraph neural network (HGNN) framework that effectively captures high-order relationships in reaction networks. Unlike GNNs, which require constructing complete graphs for multi-reactant reactions, ChemHGNN naturally models multi-reactant reactions through hyperedges, enabling more expressive reaction representations. To address key challenges, such as combinatorial explosion, model collapse, and chemically invalid negative samples, we introduce a reaction center-aware negative sampling strategy (RCNS) and a hierarchical embedding approach combining molecule, reaction and hypergraph level features. Experiments on the USPTO dataset demonstrate that ChemHGNN significantly outperforms HGNN and GNN baselines, particularly in large-scale settings, while maintaining interpretability and chemical plausibility. Our work establishes HGNNs as a superior alternative to GNNs for reaction virtual screening and discovery, offering a chemically informed framework for accelerating reaction discovery.