# Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing

arXiv: https://arxiv.org/abs/2511.08080 · HTML: https://mlsanity.com/paper/2511.08080/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 6 of 6)

- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [LIMO: Latent Inceptionism for Targeted Molecule Generation](https://mlsanity.com/paper/2206.09010/) (2022)
- [Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model](https://mlsanity.com/paper/2211.10590/) (2022)
- [Evaluating Self-Supervised Learning for Molecular Graph Embeddings](https://mlsanity.com/paper/2206.08005/) (2022)
- [BARTSmiles: Generative Masked Language Models for Molecular Representations](https://mlsanity.com/paper/2211.16349/) (2022)
- [String-based Molecule Generation via Multi-decoder VAE](https://mlsanity.com/paper/2208.10718/) (2022)

## Abstract (arXiv)

Property-constrained molecular generation and editing are crucial in AI-driven drug discovery but remain hindered by two factors: (i) capturing the complex relationships between molecular structures and multiple properties remains challenging, and (ii) the narrow coverage and incomplete annotations of molecular properties weaken the effectiveness of property-based models. To tackle these limitations, we propose HSPAG, a data-efficient framework featuring hierarchical structure-property alignment. By treating SMILES and molecular properties as complementary modalities, the model learns their relationships at atom, substructure, and whole-molecule levels. Moreover, we select representative samples through scaffold clustering and hard samples via an auxiliary variational auto-encoder (VAE), substantially reducing the required pre-training data. In addition, we incorporate a property relevance-aware masking mechanism and diversified perturbation strategies to enhance generation quality under sparse annotations. Experiments demonstrate that HSPAG captures fine-grained structure-property relationships and supports controllable generation under multiple property constraints. Two real-world case studies further validate the editing capabilities of HSPAG.