MetaRTL: Meta-path Attention Enhanced Relational Table Learning
cs.AI
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/rllm-project/rllm
License: http://creativecommons.org/licenses/by/4.0/
The gist: Relational table learning has gained increasing attention with the widespread use of relational databases.
Terminology
Abstract
Relational table learning has gained increasing attention with the widespread use of relational databases. Existing methods typically rely on deep GNN or HGNN stacks, leading to high computational costs and limited performance on large real-world databases. We propose MetaRTL, a two-stage framework for scalable and expressive relational table learning. In the first stage, MetaRTL obtains initial table embeddings via lightweight pre-training. In the second stage, it performs non-parametric message passing to derive meta-path features, which are then aggregated by an attention module, MetaAttn. By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency. Experiments on 10 real-world datasets across 24 tasks demonstrate the effectiveness of the proposed method.
Sources
- rLLM: Relational Table Learning with LLMs
- TLSQL: Table Learning Structured Query Language
- Supervised Learning on Relational Databases with Graph Neural Networks
- Boosting Relational Deep Learning with Pretrained Tabular Models
- Graph Transformers for Large Graphs
- LakeMLB: Data Lake Machine Learning Benchmark
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection