From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yuhan, Xi, Nuwa, Du, Yanrui, Wang, Haochun, Chen, Jianyu, Zhao, Sendong, Qin, Bing
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916146060460032
author Chen, Yuhan
Xi, Nuwa
Du, Yanrui
Wang, Haochun
Chen, Jianyu
Zhao, Sendong
Qin, Bing
author_facet Chen, Yuhan
Xi, Nuwa
Du, Yanrui
Wang, Haochun
Chen, Jianyu
Zhao, Sendong
Qin, Bing
contents Molecule discovery serves as a cornerstone in numerous scientific domains, fueling the development of new materials and innovative drug designs. Recent developments of in-silico molecule discovery have highlighted the promising results of cross-modal techniques, which bridge molecular structures with their descriptive annotations. However, these cross-modal methods frequently encounter the issue of data scarcity, hampering their performance and application. In this paper, we address the low-resource challenge by utilizing artificially-real data generated by Large Language Models (LLMs). We first introduce a retrieval-based prompting strategy to construct high-quality pseudo data, then explore the optimal method to effectively leverage this pseudo data. Experiments show that using pseudo data for domain adaptation outperforms all existing methods, while also requiring a smaller model scale, reduced data size and lower training cost, highlighting its efficiency. Furthermore, our method shows a sustained improvement as the volume of pseudo data increases, revealing the great potential of pseudo data in advancing low-resource cross-modal molecule discovery. Our code and data are available at https://github.com/SCIR-HI/ArtificiallyR2R.
format Preprint
id arxiv_https___arxiv_org_abs_2309_05203
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
Chen, Yuhan
Xi, Nuwa
Du, Yanrui
Wang, Haochun
Chen, Jianyu
Zhao, Sendong
Qin, Bing
Computation and Language
Molecule discovery serves as a cornerstone in numerous scientific domains, fueling the development of new materials and innovative drug designs. Recent developments of in-silico molecule discovery have highlighted the promising results of cross-modal techniques, which bridge molecular structures with their descriptive annotations. However, these cross-modal methods frequently encounter the issue of data scarcity, hampering their performance and application. In this paper, we address the low-resource challenge by utilizing artificially-real data generated by Large Language Models (LLMs). We first introduce a retrieval-based prompting strategy to construct high-quality pseudo data, then explore the optimal method to effectively leverage this pseudo data. Experiments show that using pseudo data for domain adaptation outperforms all existing methods, while also requiring a smaller model scale, reduced data size and lower training cost, highlighting its efficiency. Furthermore, our method shows a sustained improvement as the volume of pseudo data increases, revealing the great potential of pseudo data in advancing low-resource cross-modal molecule discovery. Our code and data are available at https://github.com/SCIR-HI/ArtificiallyR2R.
title From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
topic Computation and Language
url https://arxiv.org/abs/2309.05203