RelPrism: Multi-Faceted Self-Supervised Learning on Relational Databases
cs.LG
Submitted: 2026-05-22
Updated: 2026-11-17
Terminology
Sources
- SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
- RelGNN: Composite Message Passing for Relational Deep Learning
- A Closer Look at Few-shot Classification
- Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data
- Supervised Learning on Relational Databases with Graph Neural Networks
- Relational Graph Transformer
- Relational Deep Learning: Graph Representation Learning on Relational Databases
- TabPFN-3: Technical Report
- Unsupervised Learning via Meta-Learning
- STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
- Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
- Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
- SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
- A Pre-training Framework for Relational Data with Information-theoretic Principles
- Deep Graph Infomax
- Griffin: Towards a Graph-Centric Relational Database Foundation Model
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis