SOURCE-LINKED INTELLIGENCE

MetaRTL: Meta-path Attention Enhanced Relational Table Learning

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global