Metraipolis › archive › dc_ea6f0a244187
Learning Across Temporal Graph Representation Silos — arXiv:2610.19576
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19576
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:15:36.023Z
- SHA-256 of the archived text
c00c2fd8ac5bf72a5903ecb7fef7fd6d2224246e2ee15c7b51482885f99efb4b- Stable URL of this page
https://metraipolis.com/documento/dc_ea6f0a244187
How to cite
Learning Across Temporal Graph Representation Silos — arXiv:2610.19576 — arXiv (en), https://arxiv.org/abs/2610.19576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea6f0a244187 (Metraipolis archive dc_ea6f0a244187, sha256 c00c2fd8ac5bf72a5903ecb7fef7fd6d2224246e2ee15c7b51482885f99efb4b)
BibTeX
@misc{dcea6f0a244187,
title = {Learning Across Temporal Graph Representation Silos — arXiv:2610.19576},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19576},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea6f0a244187; sha256 c00c2fd8ac5bf72a5903ecb7fef7fd6d2224246e2ee15c7b51482885f99efb4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains unclear. This study investigates whether predictive structure learned from relational histories can be reused between continuous-time dynamic graphs (CTDGs) and temporal knowledge graphs (TKGs). Bidirectional reuse emerges while retaining distinct input and prediction interfaces and independent vocabularies, and sources with the same representation are not always more useful. Controlled reorganizations of source histories show that the organization contributing to reuse varies across source-target conditions. We show that learned aspects of Relational Dynamics, the predictive structure present in relational histories, can be reused across conventional representation boundaries. Independently pretrained TKG and CTDG learners can also be fused at the score level to improve prediction on a third dataset without entity or relation-semantic alignment. Two proofs of concept in recommendation and security detection illustrate that external temporal sources without direct alignment can also become useful pretraining resources. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19576 — 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 2026-10-15T13:53:35.616Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).