SupSiam：用于分子构象学习的非对比辅助损失
SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers
摘要：
我们调查暹罗网络学习相关的嵌入扩增样本的分子构象。我们发现，一个非对比（仅正对）辅助任务有助于监督训练的欧几里得神经网络（E3 NN），并增加流形光滑度（MS）周围的点云几何形状。我们证明了这种属性的多个药物活性预测任务，同时保持相关的性能指标，并提出了扩展MS的概率和回归设置。我们提供了一个表示坍塌的分析，发现任务加权，潜在的尺寸，和正规化的实质性影响。我们期望所提出的协议，以帮助可靠的E3NN分子构象的发展，即使是小数据的药物发现计划。
英文摘要：
We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task aids in supervised training of Euclidean neural networks (E3NNs) and increases manifold smoothness (MS) around point-cloud geometries. We demonstrate this property for multiple drug-activity prediction tasks while maintaining relevant performance metrics, and propose an extension of MS to probabilistic and regression settings. We provide an analysis of representation collapse, finding substantial effects of task-weighting, latent dimension, and regularization. We expect the presented protocol to aid in the development of reliable E3NNs from molecular conformers, even for small-data drug discovery programs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
