AI Paper Atlas

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

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 2 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
EquiVSet_copula (energy-based set function) instead of PGMPGM · Amazon ToysMJC: 0.441 -> 0.680Improved
EquiVSet_copula instead of PGMPGM · Amazon GearMJC: 0.471 -> 0.700Improved
EquiVSet_copula instead of PGMPGM · Amazon FurnitureMJC: 0.175 -> 0.172No clear effect
EquiVSet_copula instead of PGMPGM · Amazon CarseatsMJC: 0.230 -> 0.210Hurt
explicit set function learning (EquiVSet_copula) instead of DeepSet NoSetFnDeepSet · Amazon BathMJC: 0.424 -> 0.757Improved
Gaussian copula variational distribution instead of independent (EquiVSet_ind) (ablation)EquiVSet_ind · Amazon GearMJC: 0.610 -> 0.700Improved
Gaussian copula instead of independent variational distribution (ablation)EquiVSet_ind · Double MNISTMJC: 0.410 -> 0.588Improved
Gaussian copula instead of independent variational distribution (ablation)EquiVSet_ind · CelebAMJC: 0.530 -> 0.555Improved
Gaussian copula instead of independent variational distribution (ablation)EquiVSet_ind · PDBBindMJC: 0.355 -> 0.354No clear effect
Gaussian copula instead of independent variational distribution (ablation)EquiVSet_ind · BindingDBMJC: 0.190 -> 0.188No clear effect
EquiVSet_copula instead of PGMPGM · Double MNISTMJC: 0.300 -> 0.588Improved
EquiVSet_copula instead of PGMPGM · PDBBindMJC: 0.350 -> 0.354No clear effect

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