Research map / Graph learning / Knowledge and temporal graphs
High dimensional, tabular deep learning with an auxiliary knowledge graph
Camilo Ruiz, Hongyu Ren, Kexin Huang, 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 |
|---|---|---|---|
| PLATO versus best baseline XGBoost | PLATO · PDAC (d>>n) | PearsonR: 0.363 -> 0.400 | Improved |
| replace updated embeddings Q with general embeddings M (remove trainable message passing) (ablation) | PLATO · BRCA | PearsonR: 0.522 -> 0.583 | Improved |
| add general feature embeddings M versus no embeddings (ablation) | PLATO · BRCA | PearsonR: 0.240 -> 0.522 | Improved |
| use feature-only KG instead of no KG (ablation) | PLATO · BRCA | PearsonR: 0.240 -> 0.539 | Improved |
| use full KG with broader domain nodes instead of feature-only KG (ablation) | PLATO · BRCA | PearsonR: 0.539 -> 0.583 | Improved |
| remove 50% of KG edges (ablation) | PLATO · BRCA | PearsonR: 0.583 -> 0.412 | Hurt |
| remove 10% of KG edges (ablation) | PLATO · BRCA | PearsonR: 0.583 -> 0.570 | No clear effect |
| use only inferred first layer (PLATO-LR) instead of MLP layers 2..L (ablation) | PLATO · BRCA | PearsonR: 0.583 -> 0.550 | Hurt |
| switch KG embedding from ComplEx to TransE (ablation) | PLATO · BRCA | PearsonR: 0.583 -> 0.582 | No clear effect |
| switch KG embedding from ComplEx to DistMult (ablation) | PLATO · BRCA | PearsonR: 0.583 -> 0.575 | No clear effect |
| PLATO versus XGBoost when d is close to n | PLATO · ME (d~n) | PearsonR: 0.875 -> 0.875 | No clear effect |
| PLATO versus XGBoost when d is close to n | PLATO · NSCLC (d~n) | PearsonR: 0.843 -> 0.839 | Hurt |
Closest papers by meaning
- TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization (AAAI 2025 · similarity 0.86)
- TabM: Advancing tabular deep learning with parameter-efficient ensembling (ICLR 2025 · similarity 0.86)
- Better by default: Strong pre-tuned MLPs and boosted trees on tabular data (NeurIPS 2024 · similarity 0.86)
- Making Pre-trained Language Models Great on Tabular Prediction (ICLR 2024 · similarity 0.85)
- TabR: Tabular Deep Learning Meets Nearest Neighbors (ICLR 2024 · similarity 0.85)
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings (NeurIPS 2025 · similarity 0.85)
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.
