Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Enhanced Representation for Tabular Data via Neighborhood Propagation
Kounianhua Du, Weinan Zhang, Ruiwen Zhou, Yangkun Wang, Xilong Zhao, Jiarui Jin, Quan Gan, Zheng Zhang, David Wipf
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 |
|---|---|---|---|
| remove edge label embeddings and edge operations (ablation) | PET · Tmall CTR (10% sample) | AUC: 0.9279 -> 0.9291 | Mixed |
| remove edge label embeddings and edge operations (ablation) | PET · Taobao CTR (10% sample) | AUC: 0.8762 -> 0.8665 | Hurt |
| remove edge label embeddings and edge operations (ablation) | PET · Alipay CTR (10% sample) | AUC: 0.8720 -> 0.8558 | Hurt |
| remove node label initialization (constant vectors) (ablation) | PET · Tmall CTR (10% sample) | AUC: 0.9279 -> 0.9233 | Hurt |
| remove node label initialization (constant vectors) (ablation) | PET · Taobao CTR (10% sample) | AUC: 0.8762 -> 0.8431 | Hurt |
| remove node label initialization (constant vectors) (ablation) | PET · Alipay CTR (10% sample) | AUC: 0.8720 -> 0.8518 | Hurt |
| relevance retrieval instead of random retrieval (ablation) | PET · Tmall CTR | AUC: 0.8433 -> 0.9324 | Improved |
| relevance retrieval instead of random retrieval (ablation) | PET · Taobao CTR | AUC: 0.6544 -> 0.8838 | Improved |
| relevance retrieval instead of random retrieval (ablation) | PET · Alipay CTR | AUC: 0.7271 -> 0.8930 | Improved |
| relevance retrieval instead of random retrieval (ablation) | PET · Tmall CTR | LogLoss: 0.4922 -> 0.3321 | Improved |
| PET without edge labels vs RIM baseline (ablation) | PET w/o edge labels · Alipay CTR (10% sample) | AUC: 0.7845 -> 0.8558 | Improved |
| PET without node labels compared with RIM baseline (ablation) | PET w/o node labels · Taobao CTR (10% sample) | AUC: 0.8587 -> 0.8431 | Hurt |
Closest papers by meaning
- Large Scale Transfer Learning for Tabular Data via Language Modeling (NeurIPS 2024 · similarity 0.86)
- Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images (ICML 2024 · similarity 0.85)
- Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later (ICLR 2025 · similarity 0.85)
- TabR: Tabular Deep Learning Meets Nearest Neighbors (ICLR 2024 · similarity 0.84)
- TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization (AAAI 2025 · similarity 0.84)
- Retrieval & Fine-Tuning for In-Context Tabular Models (NeurIPS 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.
