Research map / Label-efficient and robust learning / OOD and anomaly detection
Learning Molecular Semantic Invariant Representation with Prototype Constraint
Zhiqiang Li, Jianqing Liang, Zhiqiang Wang, Xizhao Luo, Jiye Liang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic consistency loss Lsem (ablation) | MoSIR · GOOD-ZINC scaffold covariate | MAE: 0.0986 -> 0.0913 | Improved |
| add semantic consistency loss Lsem (ablation) | MoSIR · GOOD-ZINC scaffold concept | MAE: 0.0617 -> 0.0553 | Improved |
| add semantic consistency loss Lsem (ablation) | MoSIR · GOOD-ZINC size covariate | MAE: 0.1413 -> 0.1317 | Improved |
| add semantic consistency loss Lsem (ablation) | MoSIR · GOOD-ZINC size concept | MAE: 0.0712 -> 0.0637 | Improved |
| add semantic invariant loss Linv (ablation) | MoSIR · GOOD-ZINC scaffold covariate | MAE: 0.0959 -> 0.0913 | Improved |
| add semantic invariant loss Linv (ablation) | MoSIR · GOOD-ZINC scaffold concept | MAE: 0.0589 -> 0.0553 | Improved |
| add semantic invariant loss Linv (ablation) | MoSIR · GOOD-ZINC size covariate | MAE: 0.1378 -> 0.1317 | Improved |
| add semantic invariant loss Linv (ablation) | MoSIR · GOOD-ZINC size concept | MAE: 0.0674 -> 0.0637 | Improved |
| increase number of prototypes K from 5 to 20 (ablation) | MoSIR · GOOD-ZINC scaffold covariate | MAE: 0.1089 -> 0.0913 | Improved |
| increase number of prototypes K from 20 to 40 (ablation) | MoSIR · GOOD-ZINC scaffold covariate | MAE: 0.0913 -> 0.0951 | Hurt |
| replace CFD with MoSIR | CFD · GOOD-HIV size concept | ROC-AUC: 79.28 -> 81.15 | Improved |
| replace CFD with MoSIR | CFD · GOOD-ZINC scaffold covariate | MAE: 0.1187 -> 0.0913 | Improved |
Closest papers by meaning
- MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts (AAAI 2024 · similarity 0.89)
- TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence (NeurIPS 2025 · similarity 0.88)
- Domain-Agnostic Molecular Generation with Chemical Feedback (ICLR 2024 · similarity 0.88)
- MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights (AAAI 2025 · similarity 0.88)
- MolVision: Molecular Property Prediction with Vision Language Models (NeurIPS 2025 · similarity 0.87)
- Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation (ICLR 2025 · similarity 0.87)
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.
