Research map / Label-efficient and robust learning / OOD and anomaly detection
Identifying Semantic Component for Robust Molecular Property Prediction
Zijian Li, Zunhong Xu, Ruichu Cai, Zhenhui Yang, Yuguang Yan, Zhifeng Hao, Guangyi Chen, Kun Zhang
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 latent substructure regularization L_r (ablation) | SCI · MoleculeNet/OGB/GOOD datasets (Figure ablation) | ROC-AUC | Improved |
| add sparsity regularization L_h on G_h (ablation) | SCI · MoleculeNet/OGB/GOOD datasets (Figure ablation) | ROC-AUC | Improved |
| add sparsity regularization L_n on G_ir (ablation) | SCI · MoleculeNet/OGB/GOOD datasets (Figure ablation) | ROC-AUC | Improved |
| add atom classifier for atom latent variable identification (ablation) | SCI · MoleculeNet/OGB/GOOD datasets (Figure ablation) | ROC-AUC | Improved |
| set alpha around 1.0 (ablation) | SCI · MoleculeNet Bace, Sider, ClinTox | ROC-AUC | Improved |
| increase beta (stronger sparsity penalty on SR substructure) (ablation) | SCI · MoleculeNet Bace, Sider, ClinTox | ROC-AUC | Hurt |
| use sparsity regularization with beta=2 instead of none (ablation) | SCI · MoleculeNet Bace, Sider, ClinTox | ROC-AUC | Improved |
| SCI versus strongest baseline OOD-GNN | SCI · OGB Molfreesolv | RMSE: 1.8100 -> 1.9484 | Hurt |
| SCI versus strongest baseline AttentiveFP | SCI · MoleculeNet HIV | ROC-AUC: 0.7662 -> 0.7546 | Hurt |
| SCI versus GSAT on GOOD-HIV scaffold | GSAT · GOOD-HIV (scaffold split) | ROC-AUC (%): 70.07 -> 72.15 | Improved |
| SCI versus best baseline on OGB Molsider | AttentiveFP · OGB Molsider (scaffold) | ROC-AUC: 0.6919 -> 0.7152 | Improved |
Closest papers by meaning
- Learning Molecular Semantic Invariant Representation with Prototype Constraint (ICML 2026 · similarity 0.89)
- Robust Heterogeneous Graph Classification for Molecular Property Prediction with Information Bottleneck (AAAI 2025 · similarity 0.89)
- Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel (ICLR 2024 · similarity 0.88)
- MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights (AAAI 2025 · similarity 0.87)
- Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations (AAAI 2025 · similarity 0.87)
- BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models (NeurIPS 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.
