paper-with-me

홈 › Papers

GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning

2023-05-28 · NeurIPS 2023 11 · Haiteng Zhao, Shengchao Liu, Chang Ma, Hannan Xu, Jie Fu, Zhi-Hong Deng, Lingpeng Kong, Qi Liu

Molecule property prediction has gained significant attention in recent years. The main bottleneck is the label insufficiency caused by expensive lab experiments. In order to alleviate this issue and to better leverage textual knowledge for tasks, this study investigates the feasibility of employing natural language instructions to accomplish molecule-related tasks in a zero-shot setting. We discover that existing molecule-text models perform poorly in this setting due to inadequate treatment of instructions and limited capacity for graphs. To overcome these issues, we propose GIMLET, which unifies language models for both graph and text data. By adopting generalized position embedding, our model is extended to encode both graph structures and instruction text without additional graph encoding modules. GIMLET also decouples encoding of the graph from tasks instructions in the attention mechanism, enhancing the generalization of graph features across novel tasks. We construct a dataset consisting of more than two thousand molecule tasks with corresponding instructions derived from task descriptions. We pretrain GIMLET on the molecule tasks along with instructions, enabling the model to transfer effectively to a broad range of tasks. Experimental results demonstrate that GIMLET significantly outperforms molecule-text baselines in instruction-based zero-shot learning, even achieving closed results to supervised GNN models on tasks such as toxcast and muv.

📄 PDF Abstract BibTeX arXiv:2306.13089

Code (1)

zhao-ht/gimlet 공식 구현 pytorch

Tasks

Property PredictionZero-Shot Learning

Similar Papers 제목 키워드 기반

Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model

2024-08-19 · Yuran Xiang, Haiteng Zhao, Chang Ma, Zhi-Hong Deng

Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current meth…

Computational chemistryDenoisingGraph GenerationMolecular Graph Generation

HIGHT: Hierarchical Graph Tokenization for Molecule-Language Alignment

2024-06-20 · Yongqiang Chen, Quanming Yao, Juzheng Zhang, James Cheng 외

Recently, there has been a surge of interest in extending the success of large language models (LLMs) from texts to molecules. Most existing approaches adopt a graph neural network to represent a molecule as a series of …

Graph Neural NetworkHallucination

Towards 3D Molecule-Text Interpretation in Language Models

2024-01-25 · Sihang Li, Zhiyuan Liu, Yanchen Luo, Xiang Wang 외

Language Models (LMs) have greatly influenced diverse domains. However, their inherent limitation in comprehending 3D molecular structures has considerably constrained their potential in the biomolecular domain. To bridg…

Instruction FollowingLanguage ModelingLanguage ModellingMolecule Captioning+2

Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing

2022-12-21 · Shengchao Liu, Weili Nie, Chengpeng Wang, Jiarui Lu 외

There is increasing adoption of artificial intelligence in drug discovery. However, existing studies use machine learning to mainly utilize the chemical structures of molecules but ignore the vast textual knowledge avail…

Contrastive LearningDrug DesignDrug DiscoveryRetrieval+1

Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models

2024-12-24 · Xuan Lin, Long Chen, Yile Wang, Xiangxiang Zeng 외

Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annot…

Machine TranslationMolecular Property PredictionMolecule CaptioningProperty Prediction+1