Rethinking transformers with convolution and graph embeddings for few-shot molecular property discovery

Luis H.M. Torres; Joel P. Arrais; Bernardete Ribeiro

doi:10.1016/j.patcog.2025.111657

ScienceGate Book Chapters

JOURNAL ARTICLE

Rethinking transformers with convolution and graph embeddings for few-shot molecular property discovery

Luis H.M. Torres Joel P. Arrais Bernardete Ribeiro

Year: 2025 Journal: Pattern Recognition Vol: 166 Pages: 111657-111657 Publisher: Elsevier BV

DOI: 10.1016/j.patcog.2025.111657

Get Full-Text PDF Get Analytical Report

Keywords:

Convolution (computer science) Graph Property (philosophy) Computer science Shot (pellet) Transformer One shot Algorithm Mathematics Artificial intelligence Theoretical computer science Materials science Voltage Engineering Electrical engineering Mechanical engineering

Metrics

Cited By

1.59

FWCI (Field Weighted Citation Impact)

Refs

0.66

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Machine Learning in Materials Science

Physical Sciences → Materials Science → Materials Chemistry

Computational Drug Discovery Methods

Physical Sciences → Computer Science → Computational Theory and Mathematics

Protein Structure and Dynamics

Life Sciences → Biochemistry, Genetics and Molecular Biology → Molecular Biology

Rethinking transformers with convolution and graph embeddings for few-shot molecular property discovery

Metrics

Citation History

Topics

Related Documents

Few-shot learning with transformers via graph embeddings for molecular property prediction

Few-shot learning via graph embeddings with convolutional networks for low-data molecular property prediction

Multi-scale cross-attention transformer via graph embeddings for few-shot molecular property prediction

Few-shot graph and smiles learning for molecular property prediction

Adaptive Transfer of Graph Neural Networks for Few-Shot Molecular Property Prediction