AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Invariant Molecular Representation in Latent Discrete Space

Xiang Zhuang, Qiang Zhang, Keyan Ding, Yatao Bian, Xiao Wang, Jingsong Lv, Hongyang Chen, Huajun Chen

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add RVQ module to ERM (ablation)ERM · GOOD-HIV scaffold covariateROC-AUC: 69.55 -> 70.18Improved
Add RVQ module to ERM (ablation)ERM · GOOD-PCBA size conceptAP: 15.60 -> 16.59Improved
Remove VQ module (ablation)Ours (RVQ invariant learning) · GOOD-HIV scaffold covariateROC-AUC: 72.93 -> 70.18Hurt
Remove VQ module (ablation)Ours (RVQ invariant learning) · GOOD-PCBA size conceptAP: 18.21 -> 17.37Hurt
Remove residual connection (ablation)Ours (RVQ invariant learning) · GOOD-PCBA size conceptAP: 18.21 -> 12.99Hurt
Remove residual connection (ablation)Ours (RVQ invariant learning) · GOOD-HIV scaffold covariateROC-AUC: 72.93 -> 72.40Hurt
Remove invariant learning objective L_inv (ablation)Ours (RVQ invariant learning) · GOOD-HIV scaffold covariateROC-AUC: 72.93 -> 70.73Hurt
Remove regularization L_reg (ablation)Ours (RVQ invariant learning) · GOOD-PCBA size covariateAP: 18.02 -> 17.33Hurt
Remove commitment loss L_cmt (ablation)Ours (RVQ invariant learning) · GOOD-HIV scaffold covariateROC-AUC: 72.93 -> 70.20Hurt
Replace own invariant objective with CIGA objective (ablation)Ours (RVQ invariant learning) · GOOD-HIV scaffold covariateROC-AUC: 72.93 -> 71.23Hurt
Replace own invariant objective with GREA objective (ablation)Ours (RVQ invariant learning) · GOOD-PCBA size conceptAP: 18.21 -> 16.86Hurt
Increase codebook size (ablation)Ours · GOOD-HIV scaffold covariateROC-AUCMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy