Supsiam: Non-contrastive auxiliary loss for learning from molecular conformers

Exploring Multiple Instance Learning (MIL): A brief survey

M Waqas, SU Ahmed, MA Tahir, J Wu… - Expert Systems with …, 2024 - Elsevier
Abstract Multiple Instance Learning (MIL) is a learning paradigm, where training instances
are arranged in sets, called bags, and only bag-level labels are available during training …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries

EM Nowara, PO Pinheiro, SP Mahajan… - arXiv preprint arXiv …, 2024 - arxiv.org
We present NEBULA, the first latent 3D generative model for scalable generation of large
molecular libraries around a seed compound of interest. Such libraries are crucial for …
相关文章 所有 3 个版本
[PDF] github.io

[PDF][PDF] MolSiam: Simple Siamese Self-supervised Representation Learning for Small Molecules

JYY Lin, P Design, M Maser, N Frey… - … 2023 Workshop on …, 2023 - sslneurips23.github.io
We investigate a self-supervised learning technique from the Simple Siamese (Sim-Siam)
Representation Learning framework on 2D molecule graphs. SimSiam does not require …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

MoleCLUEs: Optimizing Molecular Conformers by Minimization of Differentiable Uncertainty

M Maser, N Tagasovska, JH Lee, A Watkins - arXiv preprint arXiv …, 2023 - arxiv.org
Structure-based models in the molecular sciences can be highly sensitive to input
geometries and give predictions with large variance under subtle coordinate perturbations …
相关文章 所有 2 个版本