Metraipolis › archive › dc_c557dc18c1ff
MetaRTL: Meta-path Attention Enhanced Relational Table Learning — arXiv:2609.19832
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19832
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:20:39.804Z
- SHA-256 of the archived text
4ef2f36cbf05f92af616cfe193e0a10e8cb9d42418639a57a75131f68c814f53- Stable URL of this page
https://metraipolis.com/documento/dc_c557dc18c1ff
How to cite
MetaRTL: Meta-path Attention Enhanced Relational Table Learning — arXiv:2609.19832 — arXiv (en), https://arxiv.org/abs/2609.19832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c557dc18c1ff (Metraipolis archive dc_c557dc18c1ff, sha256 4ef2f36cbf05f92af616cfe193e0a10e8cb9d42418639a57a75131f68c814f53)
BibTeX
@misc{dcc557dc18c1ff,
title = {MetaRTL: Meta-path Attention Enhanced Relational Table Learning — arXiv:2609.19832},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19832},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c557dc18c1ff; sha256 4ef2f36cbf05f92af616cfe193e0a10e8cb9d42418639a57a75131f68c814f53},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.19832 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:04:13.651Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).