Metraipolis › archive › dc_48bb086cfa55
Revisiting Simple Baselines for Relational Deep Learning — arXiv:2610.20534
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20534
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:20:48.554Z
- SHA-256 of the archived text
c182925c87b0cf77534cc5d6f9941e663ac63d9c656ccb9325db724d80a2c086- Stable URL of this page
https://metraipolis.com/documento/dc_48bb086cfa55
How to cite
Revisiting Simple Baselines for Relational Deep Learning — arXiv:2610.20534 — arXiv (en), https://arxiv.org/abs/2610.20534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48bb086cfa55 (Metraipolis archive dc_48bb086cfa55, sha256 c182925c87b0cf77534cc5d6f9941e663ac63d9c656ccb9325db724d80a2c086)
BibTeX
@misc{dc48bb086cfa55,
title = {Revisiting Simple Baselines for Relational Deep Learning — arXiv:2610.20534},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20534},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48bb086cfa55; sha256 c182925c87b0cf77534cc5d6f9941e663ac63d9c656ccb9325db724d80a2c086},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Relational deep learning has emerged as a powerful paradigm for learning end-to-end predictive models over relational databases by representing them as temporal heterogeneous graphs. Recent advances based on graph neural networks and Transformers have achieved strong performance across diverse domains. However, the effectiveness of simpler relational baselines remains underexplored, making it difficult to assess how much architectural complexity is needed to achieve strong predictive performance. Motivated by the observation that predictive signals arise from target attributes, relational attributes, and historical labels, we revisit how effectively these signals can be exploited using simple propagation methods. We adapt fixed low-pass feature propagation to relational entity graphs and train an MLP for prediction. The resulting predictions are further refined using Correct-and-Smooth, a graph-based label propagation algorithm that incorporates historical labels over task-specific meta-graphs connecting target entities. Across classification and regression tasks on RelBench, an MLP trained on neighborhood-filtered features outperforms one using only target-entity features on most tasks and recovers a substantial portion of the performance of heterogeneous GNNs. Correct-and-Smooth provides further gains from historical labels, although applying it requires a separately constructed meta-graph because connections among target entities are not directly specified by the relational entity graph. Together, our studies revisit the effectiveness of established propagation methods as simple RDL baselines while identifying canonical meta-graph construction as a key challenge for effective label propagation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.20534 — 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 2026-10-15T13:53:35.774Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).