mlsanityData to 7 Oct 2026

SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers

arXiv 2302.07754 ↗First posted 15 Feb 2023cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 14 of its 29 references that are in the map. First posted on arXiv 15 Feb 2023.

Builds on

14 of 29 references.

References · 14

  1. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  3. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  5. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  6. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  7. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  8. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  9. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  10. 2021Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Dockingcited by 81
  11. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  12. 2022Understanding Collapse in Non-Contrastive Siamese Representation Learningcited by 42
2 more
  1. 2020Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inferencecited by 35
  2. 2020Molecular machine learning with conformer ensemblescited by 27

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2024On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learningcited by 3
  2. 2024NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Librariescited by 3
  3. 2023MoleCLUEs: Molecular Conformers Maximally In-Distribution for Predictive Modelscited by 0