← Back to all news
arXiv AI By Ken Zhong, Weichen Li, Zheng Wang

MetaRTL: Meta-path Attention Enhanced Relational Table Learning

Read the original on arXiv AI →

MetaRTL is a two-stage framework for relational table learning that first generates lightweight pre-trained table embeddings and then applies non‑parametric message passing to extract meta‑path features. These features are aggregated using an attention module called MetaAttn, shifting computation from deep GNN stacks to efficient meta‑path aggregation. Experiments on 10 real‑world datasets across 24 tasks show that MetaRTL achieves strong performance while reducing computational cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 27

MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection

MetaSieve is a metapath selection layer that reduces subgraph size in relational deep learning by pruning uninformative metapaths using SQL join and aggregation statistics. It scores candidate metapath extensions with a lightweight function that favors informative yet lightweight paths, discarding those below a threshold. The method is independent of GNN parameters and, when applied to the RelBench benchmark, consistently cuts per‑epoch training time while preserving or improving accuracy.

By Fahim Shahriar Khan, Ashraf Aboulnaga
benchmarksdata-engineering
More like this →
arXiv Machine Learning
Sep 14

InRTL: Effective Intra-Inter Interaction Learning for Relational Tables

InRTL: Effective Intra-Inter Interaction Learning for Relational Tables proposes a unified framework that explicitly models dependencies both within and across relational tables. The approach introduces intra-table interactions to capture associations among rows in the same table and inter-table interactions to capture dependencies between rows linked by primary key–foreign key relationships. It employs a column-aware table encoder, Transformer-based self-attention and cross-attention modules, and incorporates linearized attention and heterogeneous graph neural networks to improve scalability, demonstrating effectiveness across ten datasets and 24 real-world tasks.

By Weichen Li, Ken Zhong, Zheng Wang, Li Pan, Jianhua Li
llms
More like this →
arXiv AI
Jun 9

What Makes a Desired Graph for Relational Deep Learning?

arXiv:2606. 08491v1 Announce Type: new Abstract: Relational deep learning (RDL) converts relational databases (RDBs) into heterogeneous graphs, but graphs derived directly from database schemas are often not well suited for how graph neural networks (GNNs) perform relational reasoning.

By Yao Cheng, Siqiang Luo
safety
More like this →