Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Neural Set Functions Under the Optimal Subset Oracle
Zijing Ou, Tingyang Xu, Qinliang Su, Yingzhen Li, Peilin Zhao, Yatao Bian
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 |
|---|---|---|---|
| EquiVSet_copula (energy-based set function) instead of PGM | PGM · Amazon Toys | MJC: 0.441 -> 0.680 | Improved |
| EquiVSet_copula instead of PGM | PGM · Amazon Gear | MJC: 0.471 -> 0.700 | Improved |
| EquiVSet_copula instead of PGM | PGM · Amazon Furniture | MJC: 0.175 -> 0.172 | No clear effect |
| EquiVSet_copula instead of PGM | PGM · Amazon Carseats | MJC: 0.230 -> 0.210 | Hurt |
| explicit set function learning (EquiVSet_copula) instead of DeepSet NoSetFn | DeepSet · Amazon Bath | MJC: 0.424 -> 0.757 | Improved |
| Gaussian copula variational distribution instead of independent (EquiVSet_ind) (ablation) | EquiVSet_ind · Amazon Gear | MJC: 0.610 -> 0.700 | Improved |
| Gaussian copula instead of independent variational distribution (ablation) | EquiVSet_ind · Double MNIST | MJC: 0.410 -> 0.588 | Improved |
| Gaussian copula instead of independent variational distribution (ablation) | EquiVSet_ind · CelebA | MJC: 0.530 -> 0.555 | Improved |
| Gaussian copula instead of independent variational distribution (ablation) | EquiVSet_ind · PDBBind | MJC: 0.355 -> 0.354 | No clear effect |
| Gaussian copula instead of independent variational distribution (ablation) | EquiVSet_ind · BindingDB | MJC: 0.190 -> 0.188 | No clear effect |
| EquiVSet_copula instead of PGM | PGM · Double MNIST | MJC: 0.300 -> 0.588 | Improved |
| EquiVSet_copula instead of PGM | PGM · PDBBind | MJC: 0.350 -> 0.354 | No clear effect |
Closest papers by meaning
- Enhancing Neural Subset Selection: Integrating Background Information into Set Representations (ICLR 2024 · similarity 0.89)
- Learning Set Functions with Implicit Differentiation (AAAI 2025 · similarity 0.88)
- HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection (NeurIPS 2024 · similarity 0.86)
- Efficient Biological Data Acquisition through Inference Set Design (ICLR 2025 · similarity 0.82)
- Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection (ICML 2024 · similarity 0.81)
- Online Set Learning from Precision and Recall Feedback (NeurIPS 2026 · similarity 0.81)
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.
