Metraipolis › archive › dc_5ac1f044f77d

Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting — arXiv:2609.18163

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18163
License (as archived)
CC0-1.0
Archived
2026-10-15T16:16:02.695Z
SHA-256 of the archived text
043e66331c0cc7624c6088de46064397ba9fa5fb9e031a3edac303010eb6dd05
Stable URL of this page
https://metraipolis.com/documento/dc_5ac1f044f77d

How to cite

Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting — arXiv:2609.18163 — arXiv (en), https://arxiv.org/abs/2609.18163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ac1f044f77d (Metraipolis archive dc_5ac1f044f77d, sha256 043e66331c0cc7624c6088de46064397ba9fa5fb9e031a3edac303010eb6dd05)
BibTeX
@misc{dc5ac1f044f77d,
  title = {Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting — arXiv:2609.18163},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ac1f044f77d; sha256 043e66331c0cc7624c6088de46064397ba9fa5fb9e031a3edac303010eb6dd05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept semantics and graph structure separately or summarize semantics over coarse historical snapshots, leaving semantic representations potentially misaligned with rapidly evolving graph evidence. We propose a time-aligned evolving concept graph framework that jointly models semantic and structural evolution. Its core idea is to treat dated papers as shared update events, reconstructing semantic and structural states from the same publication history through each prediction time. Pair-level fusion combines these states to forecast first co-occurrence, relation formation, and conditional relation type. Holding architecture and training fixed, refreshing context alongside graph updates improves mean relation AUPRC by 16.6% over frozen context. On a graph built from 187,848 papers with 270,687 concepts and 7.45 million co-occurrence links, the complete framework improves mean relation AUROC from 0.9290 for the strongest evaluated baseline to 0.9722, with mean population-weighted AUPRC 0.005778.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.IR).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.18163 — 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 2026-10-15T15:44:55.726Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).