← Back to all news
arXiv Machine Learning By Fahim Shahriar Khan, Ashraf Aboulnaga

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

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

Related stories

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 →
arXiv AI
Sep 18

MetaRTL: Meta-path Attention Enhanced Relational Table Learning

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.

By Ken Zhong, Weichen Li, Zheng Wang
rag
More like this →
arXiv Machine Learning
Oct 8

EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks

The paper introduces EDiS, an Edge‑Disjoint Subgraph sparsification framework that separates a one‑time structural extraction of a graph into cacheable edge‑disjoint subgraphs from the per‑epoch graph composition. By recombining these cached subgraphs under edge‑budget constraints, EDiS avoids repeated sampling or recomputation while allowing varying training graphs across epochs. Experiments on 19 node‑classification benchmarks show that EDiS outperforms 17 baselines in accuracy/ROC‑AUC, achieving the lowest average rank and gap‑to‑best, especially at tight edge budgets.

By Sai Karthik Navuluru, Siddhartha Shankar Das, Franck Dernoncourt, S M Ferdous, Ryan A. Rossi, Nesreen K. Ahmed, Baris Coskunuzer, Alex Pothen, Lakshman Tamil, Mahantesh M Halappanavar
benchmarks
More like this →