Ensemble Model With Bert,Roberta and Xlnet For Molecular property prediction

TL;DR

This paper introduces an ensemble approach combining BERT, RoBERTa, and XLNet for molecular property prediction, achieving high accuracy without extensive pre-training and addressing resource limitations.

Contribution

It presents a novel ensemble method that leverages supervised fine-tuning of multiple transformer models for efficient molecular property prediction.

Findings

Significant accuracy improvements over existing models

Effective in resource-constrained environments

Enables cost-efficient molecular property prediction

Abstract

This paper presents a novel approach for predicting molecular properties with high accuracy without the need for extensive pre-training. Employing ensemble learning and supervised fine-tuning of BERT, RoBERTa, and XLNet, our method demonstrates significant effectiveness compared to existing advanced models. Crucially, it addresses the issue of limited computational resources faced by experimental groups, enabling them to accurately predict molecular properties. This innovation provides a cost-effective and resource-efficient solution, potentially advancing further research in the molecular domain.