Research map / Graph learning / Graph self-supervised learning
Handling Missing Data with Graph Representation Learning
Jiaxuan You, Xiaobai Ma, Yi Ding, Mykel J Kochenderfer, Jure Leskovec
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 |
|---|---|---|---|
| GRAPE vs best baseline (KNN) | feature imputation · 9 UCI datasets, 30% missing | MAE: 20% lower MAE | Improved |
| GRAPE vs best baseline (MICE) | label prediction · 9 UCI datasets, 30% missing | MAE: 10% lower MAE | Improved |
| GRAPE vs baselines at 10% missing | feature imputation · UCI, 10% missing | MAE: -8% (KNN better) | Hurt |
| add edge dropout (ablation) | GRAPE · 9 UCI imputation | MAE: 0.171 -> 0.090 (concrete); -33% avg | Improved |
| use Mean instead of Sum aggregation (ablation) | GRAPE · 9 UCI imputation | MAE: 0.134 -> 0.102 (power) | Improved |
| use Mean instead of Max aggregation (ablation) | GRAPE · 9 UCI imputation | MAE: 0.088 vs 0.090 (concrete) | No clear effect |
| end-to-end training instead of impute-then-predict (ablation) | GRAPE · UCI label prediction | MAE: 9.02 -> 4.72 (yacht); 0.004 -> 0.007 (naval) | Mixed |
| GRAPE on unseen observations without retraining | feature imputation · UCI unseen data | MAE: 21% lower MAE | Improved |
| GRAPE vs specialized discrete matrix completion IGMC | matrix completion · Flixster | RMSE: 0.872 vs 0.899 | Hurt |
Closest papers by meaning
- Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features (ICML 2025 · similarity 0.87)
- Attribute-Missing Graph Clustering Network (AAAI 2024 · similarity 0.86)
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness (NeurIPS 2026 · similarity 0.85)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.85)
- Prediction models that learn to avoid missing values (ICML 2025 · similarity 0.85)
- Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering (AAAI 2024 · 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.
