Metraipolis › archive › dc_c8fa1a28a8cd

AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas — arXiv:2611.07347

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07347
License (as archived)
CC0-1.0
Archived
2026-11-06T14:50:30.273Z
SHA-256 of the archived text
f31c95b912dd31ecdb2476484b1069997e90cfc2d9b8680fbab33b75998180e5
Stable URL of this page
https://metraipolis.com/documento/dc_c8fa1a28a8cd

How to cite

AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas — arXiv:2611.07347 — arXiv (en), https://arxiv.org/abs/2611.07347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8fa1a28a8cd (Metraipolis archive dc_c8fa1a28a8cd, sha256 f31c95b912dd31ecdb2476484b1069997e90cfc2d9b8680fbab33b75998180e5)
BibTeX
@misc{dcc8fa1a28a8cd,
  title = {AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas — arXiv:2611.07347},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07347},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8fa1a28a8cd; sha256 f31c95b912dd31ecdb2476484b1069997e90cfc2d9b8680fbab33b75998180e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Link prediction (LP) is a widely applied task in graph learning. Conventional LP approaches typically follow a dataset-specific paradigm, requiring independent training for each graph and incurring high computational and maintenance costs in large-scale applications. Motivated by these limitations, recent work explores Universal Link Prediction (ULP), aiming to enable training-free inference on arbitrary unseen graphs. However, existing methods primarily rely on subgraph sampling strategies to construct universal representations, which are unable to capture higher-order information due to the exponential growth of higher-order neighborhoods. As a result, they often under-perform on graphs where long-range signals are essential, such as biological networks. Moreover, their prediction models are typically domain-agnostic and lack the ability to adapt to different graph domains, leading to limited generalization. To address these challenges, we propose an Atlas-based Universal Link Prediction framework (AtlasULP), which introduces the relation atlas to capture structural associations between node pairs from both global and local perspectives, enabling a comprehensive characterization of connectivity signals across diverse graph domains. Building upon this representation, we develop a domain-guided prompting ULP model, which generates domain-aware prompt tokens from contextual structures and performs prompt-guided in-context prediction for adaptive link inference. Extensive experiments demonstrate that AtlasULP consistently outperforms state-of-the-art methods across diverse graph domains.

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/2611.07347 — 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 2026-11-06T14:21:42.623Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).