Research map / Probabilistic and scientific modeling / Molecules and proteins
Simultaneous Missing Value Imputation and Structure Learning with Groups
Pablo Morales-Alvarez, Wenbo Gong, Angus Lamb, Simon Woodhead, Simon Peyton Jones, Nick Pawlowski, Miltiadis Allamanis, Cheng 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 |
|---|---|---|---|
| VISL vs PVAE imputation (adds learned graph) | VISL · Synthetic | RMSE: 0.1407 -> 0.1196 | Improved |
| VISL vs MICE imputation | VISL · Neuropathic Pain | AUPR: 0.6513 -> 0.6597 | No clear effect |
| VISL vs PVAE imputation | VISL · Neuropathic Pain | AUPR: 0.5934 -> 0.6597 | Improved |
| VISL vs PVAE imputation | VISL · Eedi topics | AUROC: 0.7852 -> 0.7815 | No clear effect |
| VISL vs PVAE imputation | VISL · Eedi topics | accuracy: 0.7138 -> 0.7147 | No clear effect |
| VISL vs DAG-GNN structure learning | VISL · Synthetic | adjacency F1: 0.464 -> 0.740 | Improved |
| VISL vs NOTEARS (NL) orientation precision | VISL · Synthetic | orientation precision: 0.417 -> 0.414 | Hurt |
| VISL vs GES structure learning | VISL · Neuropathic Pain | adjacency F1: 0.176 -> 0.370 | Improved |
| VISL vs NOTEARS (NL) adjacency precision | VISL · Neuropathic Pain | adjacency precision: 0.644 -> 0.637 | Hurt |
| VISL vs DAG-GNN expert-rated adjacency | VISL · Eedi topics (Expt 1) | expert adjacency score: 2.04 -> 3.60 | Improved |
| VISL vs DAG-GNN expert-rated orientation | VISL · Eedi topics (Expt 1) | expert orientation score: 1.68 -> 2.76 | Improved |
| VISL vs Random inside level-1 topic edges | VISL · Eedi topics | fraction of edges inside level-1 topics: 34\% -> 82\% | Improved |
Closest papers by meaning
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness (NeurIPS 2026 · similarity 0.87)
- How to deal with missing data in supervised deep learning? (ICLR 2022 · similarity 0.87)
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR (NeurIPS 2026 · similarity 0.85)
- Attribute-Missing Graph Clustering Network (AAAI 2024 · similarity 0.85)
- Missing Data Imputation by Reducing Mutual Information with Rectified Flows (NeurIPS 2025 · similarity 0.84)
- Biased Incomplete Multi-View Learning (AAAI 2025 · similarity 0.84)
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.
