Metraipolis › archive › dc_fbbf3275c384

Incremental Evaluation and Training in Relational Deep Learning — arXiv:2608.13023

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13023
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:32.267Z
SHA-256 of the archived text
c6dbdb28e2f736a05a90b8b78b9582e0b78d6eb3fda1fcbc65ce1ce456ae750e
Stable URL of this page
https://metraipolis.com/documento/dc_fbbf3275c384

How to cite

Incremental Evaluation and Training in Relational Deep Learning — arXiv:2608.13023 — arXiv (en), https://arxiv.org/abs/2608.13023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbbf3275c384 (Metraipolis archive dc_fbbf3275c384, sha256 c6dbdb28e2f736a05a90b8b78b9582e0b78d6eb3fda1fcbc65ce1ce456ae750e)
BibTeX
@misc{dcfbbf3275c384,
  title = {Incremental Evaluation and Training in Relational Deep Learning — arXiv:2608.13023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbbf3275c384; sha256 c6dbdb28e2f736a05a90b8b78b9582e0b78d6eb3fda1fcbc65ce1ce456ae750e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL evaluation practices rely on static, single-episode dataset snapshots, overlooking the continuous, time-evolving nature of real-world databases. Consequently, current RDL benchmarks fail to capture how model performance changes as new data accumulates over time. To address this limitation, we introduce an incremental, multi-episode evaluation and training paradigm to assess and improve the temporal robustness and adaptability of state-of-the-art RDL models. Using established large-scale datasets, we examine data evolution and model training dynamics, demonstrating that temporal concept drifts occur in the majority of predictive tasks. We present multiple incremental training regimes for fine-tuning the models and demonstrate that transfer learning is both feasible and highly effective in the RDL setting. Alongside a new temporal evaluation metric that prioritizes near-future accuracy, we show that our incrementally fine-tuned models consistently outperform the standard, expensive, from-scratch trained baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.13023 — 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 2026-10-19T04:20:35.843Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).